Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4939 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8379. Min Range: -9.8379
Max Act: 9.8379. Min Act: -0.1700
Data Index: 8367903 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8379. Min Range: -9.8379
Max Act: 9.5879. Min Act: -0.1700
Data Index: 7920460 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8379. Min Range: -9.8379
Max Act: 9.3379. Min Act: -0.1700
Data Index: 1020903 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8379. Min Range: -9.8379
Max Act: 9.3379. Min Act: -0.1700
Data Index: 8131928 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8379. Min Range: -9.8379
Max Act: 9.1504. Min Act: -0.1700
Data Index: 5700485 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8379. Min Range: -9.8379
Max Act: 9.0879. Min Act: -0.1700
Data Index: 6781974 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8379. Min Range: -9.8379
Max Act: 9.0879. Min Act: -0.1700
Data Index: 4219563 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8379. Min Range: -9.8379
Max Act: 9.0879. Min Act: -0.1700
Data Index: 2305453 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8379. Min Range: -9.8379
Max Act: 9.0254. Min Act: -0.1700
Data Index: 2760028 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.9629. Min Act: -0.1700
Data Index: 4044046 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.9004. Min Act: -0.1700
Data Index: 5010631 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.9004. Min Act: -0.1700
Data Index: 6682957 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.8379. Min Act: -0.1700
Data Index: 6440743 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.8379. Min Act: -0.1700
Data Index: 1335349 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.8379. Min Act: -0.1700
Data Index: 2350117 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.8379. Min Act: -0.1700
Data Index: 5324473 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.7754. Min Act: -0.1700
Data Index: 7848139 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.7754. Min Act: -0.1700
Data Index: 6017856 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.7754. Min Act: -0.1700
Data Index: 7412310 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8379. Min Range: -9.8379
Max Act: 8.7754. Min Act: -0.1700
Data Index: 6624717 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19