Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3422 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.6930. Min Act: -0.1700
Data Index: 1366031 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.4430. Min Act: -0.1700
Data Index: 5728608 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.4742. Min Act: -0.1700
Data Index: 1222432 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.4430. Min Act: -0.1700
Data Index: 576968 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.4430. Min Act: -0.1700
Data Index: 576963 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.4430. Min Act: -0.1700
Data Index: 6925616 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.4430. Min Act: -0.1700
Data Index: 3601062 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.4117. Min Act: -0.1700
Data Index: 6202880 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.4430. Min Act: -0.1700
Data Index: 8701183 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.4117. Min Act: -0.1700
Data Index: 5042638 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.4117. Min Act: -0.1700
Data Index: 8059581 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.4117. Min Act: -0.1700
Data Index: 1800516 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.4117. Min Act: -0.1700
Data Index: 2246122 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.3805. Min Act: -0.1700
Data Index: 6039157 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.3805. Min Act: -0.1700
Data Index: 8347880 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.3805. Min Act: -0.1700
Data Index: 2111844 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.3805. Min Act: -0.1700
Data Index: 2324656 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.3805. Min Act: -0.1700
Data Index: 7715232 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.3805. Min Act: -0.1699
Data Index: 8295621 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6930. Min Range: -5.6930
Max Act: 5.3492. Min Act: -0.1700
Data Index: 7005933 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19