Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2450 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.4786. Min Act: -0.1700
Data Index: 5861063 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.4473. Min Act: -0.1700
Data Index: 7848612 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.4160. Min Act: -0.1700
Data Index: 291276 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.4160. Min Act: -0.1700
Data Index: 731013 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.4316. Min Act: -0.1700
Data Index: 1309665 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.4003. Min Act: -0.1700
Data Index: 4154940 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.4003. Min Act: -0.1700
Data Index: 8134180 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.3846. Min Act: -0.1700
Data Index: 4514469 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.3689. Min Act: -0.1700
Data Index: 7272885 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.3689. Min Act: -0.1700
Data Index: 7399391 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.3689. Min Act: -0.1700
Data Index: 3565738 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.3375. Min Act: -0.1700
Data Index: 3167793 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.3218. Min Act: -0.1700
Data Index: 3463059 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.3532. Min Act: -0.1700
Data Index: 5280795 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.3532. Min Act: -0.1700
Data Index: 8068166 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.3375. Min Act: -0.1700
Data Index: 8206271 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.3375. Min Act: -0.1700
Data Index: 496521 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.3218. Min Act: -0.1700
Data Index: 5680442 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.3062. Min Act: -0.1700
Data Index: 1107258 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4786. Min Range: -3.4786
Max Act: 3.3062. Min Act: -0.1700
Data Index: 3625692 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19