Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2266 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.4336. Min Act: -0.1700
Data Index: 1910475 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.2610. Min Act: -0.1700
Data Index: 7160063 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.2453. Min Act: -0.1700
Data Index: 7160062 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.2453. Min Act: -0.1700
Data Index: 829758 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.2138. Min Act: -0.1700
Data Index: 823210 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.1981. Min Act: -0.1700
Data Index: 3895497 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.1981. Min Act: -0.1700
Data Index: 7857779 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.1666. Min Act: -0.1700
Data Index: 2066716 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.1666. Min Act: -0.1700
Data Index: 1126941 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.1352. Min Act: -0.1700
Data Index: 6020595 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.1194. Min Act: -0.1700
Data Index: 823211 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.1037. Min Act: -0.1700
Data Index: 3338744 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.1194. Min Act: -0.1700
Data Index: 4563469 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.1037. Min Act: -0.1700
Data Index: 6605532 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.1037. Min Act: -0.1700
Data Index: 6639304 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.1037. Min Act: -0.1700
Data Index: 6553798 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.0879. Min Act: -0.1700
Data Index: 6113008 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.1037. Min Act: -0.1700
Data Index: 5343578 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.0879. Min Act: -0.1700
Data Index: 8532441 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4336. Min Range: -3.4336
Max Act: 3.0721. Min Act: -0.1700
Data Index: 571002 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19