Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4767 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.8384. Min Act: -0.1700
Data Index: 1119220 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.8072. Min Act: -0.1700
Data Index: 6586871 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.7446. Min Act: -0.1700
Data Index: 1502724 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.6820. Min Act: -0.1700
Data Index: 4031718 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.6820. Min Act: -0.1700
Data Index: 370500 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.6820. Min Act: -0.1700
Data Index: 582610 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.6507. Min Act: -0.1700
Data Index: 8552191 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.6038. Min Act: -0.1700
Data Index: 370504 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.5568. Min Act: -0.1700
Data Index: 8092666 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.5412. Min Act: -0.1700
Data Index: 7025161 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.5099. Min Act: -0.1700
Data Index: 4625176 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.5099. Min Act: -0.1700
Data Index: 3288274 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.5099. Min Act: -0.1700
Data Index: 2006524 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.5099. Min Act: -0.1700
Data Index: 5277495 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.5099. Min Act: -0.1700
Data Index: 7544667 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.4785. Min Act: -0.1700
Data Index: 4758548 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.4785. Min Act: -0.1700
Data Index: 7551015 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.4785. Min Act: -0.1700
Data Index: 6393145 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.4629. Min Act: -0.1700
Data Index: 1850630 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8384. Min Range: -3.8384
Max Act: 3.4629. Min Act: -0.1700
Data Index: 3210866 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19