Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3640 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.8029. Min Act: -0.1700
Data Index: 571386 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.7857. Min Act: -0.1700
Data Index: 8798191 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.7253. Min Act: -0.1700
Data Index: 4747301 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.7253. Min Act: -0.1698
Data Index: 1041834 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.7339. Min Act: -0.1698
Data Index: 1017530 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.7166. Min Act: -0.1700
Data Index: 8798189 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.7080. Min Act: -0.1700
Data Index: 2068007 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.6646. Min Act: -0.1700
Data Index: 2981342 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.6472. Min Act: -0.1700
Data Index: 5704535 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.6472. Min Act: -0.1698
Data Index: 5827616 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.6559. Min Act: -0.1699
Data Index: 1586949 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.6559. Min Act: -0.1700
Data Index: 6758609 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.6472. Min Act: -0.1700
Data Index: 3077170 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.6385. Min Act: -0.1700
Data Index: 3215779 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.6472. Min Act: -0.1700
Data Index: 658124 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.6298. Min Act: -0.1699
Data Index: 8068124 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.6123. Min Act: -0.1686
Data Index: 6877338 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.6123. Min Act: -0.1700
Data Index: 7907778 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.6210. Min Act: -0.1700
Data Index: 2250389 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8029. Min Range: -1.8029
Max Act: 1.6123. Min Act: -0.1700
Data Index: 6166206 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19