Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3573 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.8829. Min Act: -0.1700
Data Index: 3889448 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.8204. Min Act: -0.1700
Data Index: 7357365 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.7579. Min Act: -0.1700
Data Index: 117049 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.5704. Min Act: -0.1700
Data Index: 655717 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.5704. Min Act: -0.1700
Data Index: 3625640 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.5079. Min Act: -0.1700
Data Index: 1737034 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.5079. Min Act: -0.1700
Data Index: 1259353 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.5079. Min Act: -0.1700
Data Index: 1834084 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.4454. Min Act: -0.1700
Data Index: 964360 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.4454. Min Act: -0.1700
Data Index: 1193466 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.3829. Min Act: -0.1700
Data Index: 3246872 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.3829. Min Act: -0.1700
Data Index: 4317816 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.3204. Min Act: -0.1700
Data Index: 8055575 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.3204. Min Act: -0.1700
Data Index: 6965686 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.3204. Min Act: -0.1700
Data Index: 770472 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.2579. Min Act: -0.1700
Data Index: 6851413 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.2579. Min Act: -0.1700
Data Index: 3870187 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.1954. Min Act: -0.1700
Data Index: 1809076 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.1954. Min Act: -0.1700
Data Index: 2452320 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8829. Min Range: -10.8829
Max Act: 10.1954. Min Act: -0.1700
Data Index: 5305056 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19