Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 789 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.8896. Min Act: -0.1700
Data Index: 5518372 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.8271. Min Act: -0.1700
Data Index: 2906507 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.7958. Min Act: -0.1700
Data Index: 7560897 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.7958. Min Act: -0.1700
Data Index: 3163655 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.7958. Min Act: -0.1700
Data Index: 1971328 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.7958. Min Act: -0.1700
Data Index: 8059006 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.7332. Min Act: -0.1700
Data Index: 8553419 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.7332. Min Act: -0.1700
Data Index: 1776223 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.7332. Min Act: -0.1700
Data Index: 6356866 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.6707. Min Act: -0.1700
Data Index: 5434393 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.6863. Min Act: -0.1700
Data Index: 1649186 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.6707. Min Act: -0.1700
Data Index: 4697921 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.6394. Min Act: -0.1700
Data Index: 3904761 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.6550. Min Act: -0.1700
Data Index: 1559006 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.6394. Min Act: -0.1700
Data Index: 6371457 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.6237. Min Act: -0.1700
Data Index: 5581912 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.5924. Min Act: -0.1700
Data Index: 2506800 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.6081. Min Act: -0.1700
Data Index: 6298715 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.5768. Min Act: -0.1700
Data Index: 5654937 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8896. Min Range: -3.8896
Max Act: 3.6081. Min Act: -0.1700
Data Index: 4415375 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19