Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3395. Min Range: -7.3395
Max Act: 7.3395. Min Act: -0.1700
Data Index: 785503 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3395. Min Range: -7.3395
Max Act: 7.2770. Min Act: -0.1700
Data Index: 6977376 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3395. Min Range: -7.3395
Max Act: 7.2458. Min Act: -0.1700
Data Index: 3636765 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3395. Min Range: -7.3395
Max Act: 7.1833. Min Act: -0.1700
Data Index: 8059286 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3395. Min Range: -7.3395
Max Act: 7.1208. Min Act: -0.1700
Data Index: 5919467 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3395. Min Range: -7.3395
Max Act: 7.1208. Min Act: -0.1700
Data Index: 7241585 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3395. Min Range: -7.3395
Max Act: 7.0895. Min Act: -0.1700
Data Index: 8216256 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3395. Min Range: -7.3395
Max Act: 7.0895. Min Act: -0.1700
Data Index: 4067536 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3395. Min Range: -7.3395
Max Act: 7.0583. Min Act: -0.1700
Data Index: 6401224 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3395. Min Range: -7.3395
Max Act: 6.9645. Min Act: -0.1700
Data Index: 2144864 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3395. Min Range: -7.3395
Max Act: 6.9645. Min Act: -0.1700
Data Index: 7366733 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3395. Min Range: -7.3395
Max Act: 6.8395. Min Act: -0.1700
Data Index: 6469882 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3395. Min Range: -7.3395
Max Act: 6.8395. Min Act: -0.1700
Data Index: 1427426 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3395. Min Range: -7.3395
Max Act: 6.8708. Min Act: -0.1700
Data Index: 5455738 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3395. Min Range: -7.3395
Max Act: 6.8395. Min Act: -0.1700
Data Index: 8164527 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3395. Min Range: -7.3395
Max Act: 6.8083. Min Act: -0.1700
Data Index: 5696512 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3395. Min Range: -7.3395
Max Act: 6.8083. Min Act: -0.1700
Data Index: 5196883 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3395. Min Range: -7.3395
Max Act: 6.8395. Min Act: -0.1700
Data Index: 1537621 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3395. Min Range: -7.3395
Max Act: 6.8083. Min Act: -0.1700
Data Index: 1612795 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3395. Min Range: -7.3395
Max Act: 6.7770. Min Act: -0.1700
Data Index: 8420191 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19