Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1457 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.4108. Min Act: -0.1700
Data Index: 634959 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.3796. Min Act: -0.1700
Data Index: 4544796 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.3483. Min Act: -0.1700
Data Index: 144429 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.3171. Min Act: -0.1700
Data Index: 2271607 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.2858. Min Act: -0.1700
Data Index: 6211313 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.2233. Min Act: -0.1700
Data Index: 4824123 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.2233. Min Act: -0.1700
Data Index: 1082987 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.1921. Min Act: -0.1700
Data Index: 8345015 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.1921. Min Act: -0.1700
Data Index: 7509351 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.1921. Min Act: -0.1700
Data Index: 6171504 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.1296. Min Act: -0.1700
Data Index: 328679 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.1608. Min Act: -0.1700
Data Index: 2910539 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.1296. Min Act: -0.1700
Data Index: 8700287 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.0983. Min Act: -0.1700
Data Index: 662662 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.0983. Min Act: -0.1700
Data Index: 8774294 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.0671. Min Act: -0.1700
Data Index: 3885325 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.0671. Min Act: -0.1700
Data Index: 475783 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.0358. Min Act: -0.1700
Data Index: 6747209 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.0358. Min Act: -0.1700
Data Index: 4539059 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4108. Min Range: -6.4108
Max Act: 6.0358. Min Act: -0.1700
Data Index: 1736675 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19