Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2411 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.1978. Min Act: -0.1700
Data Index: 5837207 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.1665. Min Act: -0.1700
Data Index: 8113949 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.1353. Min Act: -0.1700
Data Index: 579125 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.1353. Min Act: -0.1700
Data Index: 7085828 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.1040. Min Act: -0.1700
Data Index: 181079 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.0728. Min Act: -0.1700
Data Index: 27233 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.1040. Min Act: -0.1700
Data Index: 902249 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.0415. Min Act: -0.1700
Data Index: 4895306 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.0728. Min Act: -0.1700
Data Index: 1009355 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.0728. Min Act: -0.1700
Data Index: 354930 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.0728. Min Act: -0.1700
Data Index: 8576550 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.0415. Min Act: -0.1700
Data Index: 2911065 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.0728. Min Act: -0.1700
Data Index: 7364713 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.0728. Min Act: -0.1700
Data Index: 2272745 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.0103. Min Act: -0.1700
Data Index: 226685 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.0415. Min Act: -0.1700
Data Index: 1828317 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.0103. Min Act: -0.1700
Data Index: 112072 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.0415. Min Act: -0.1700
Data Index: 3897802 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.0415. Min Act: -0.1700
Data Index: 3376316 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1978. Min Range: -4.1978
Max Act: 4.0415. Min Act: -0.1700
Data Index: 3572144 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19