Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1137 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.8364. Min Act: -0.1700
Data Index: 7143827 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.7113. Min Act: -0.1700
Data Index: 6312428 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.7113. Min Act: -0.1700
Data Index: 8096280 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.6956. Min Act: -0.1700
Data Index: 4450468 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.6956. Min Act: -0.1700
Data Index: 5117163 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.6643. Min Act: -0.1700
Data Index: 94262 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.6487. Min Act: -0.1700
Data Index: 8128800 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.6487. Min Act: -0.1700
Data Index: 3367610 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.6487. Min Act: -0.1700
Data Index: 8313262 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.6487. Min Act: -0.1700
Data Index: 252943 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.6174. Min Act: -0.1700
Data Index: 218908 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.6174. Min Act: -0.1700
Data Index: 4868604 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.6174. Min Act: -0.1700
Data Index: 2995592 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.6174. Min Act: -0.1700
Data Index: 6727617 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.6330. Min Act: -0.1700
Data Index: 6733182 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.6017. Min Act: -0.1700
Data Index: 8802819 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.6017. Min Act: -0.1700
Data Index: 4741669 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.6017. Min Act: -0.1700
Data Index: 5242108 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.5861. Min Act: -0.1700
Data Index: 3261965 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8364. Min Range: -3.8364
Max Act: 3.5704. Min Act: -0.1700
Data Index: 3520094 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19