Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1428 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3524. Min Range: -6.3524
Max Act: 6.3524. Min Act: -0.1700
Data Index: 3933993 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3524. Min Range: -6.3524
Max Act: 5.8524. Min Act: -0.1700
Data Index: 360785 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3524. Min Range: -6.3524
Max Act: 5.7899. Min Act: -0.1700
Data Index: 6265618 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3524. Min Range: -6.3524
Max Act: 5.6961. Min Act: -0.1700
Data Index: 2807867 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3524. Min Range: -6.3524
Max Act: 5.6961. Min Act: -0.1700
Data Index: 3673417 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3524. Min Range: -6.3524
Max Act: 5.6649. Min Act: -0.1700
Data Index: 411686 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3524. Min Range: -6.3524
Max Act: 5.6336. Min Act: -0.1700
Data Index: 3133153 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3524. Min Range: -6.3524
Max Act: 5.6024. Min Act: -0.1700
Data Index: 4755556 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3524. Min Range: -6.3524
Max Act: 5.6336. Min Act: -0.1700
Data Index: 3952721 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3524. Min Range: -6.3524
Max Act: 5.5711. Min Act: -0.1700
Data Index: 6265617 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3524. Min Range: -6.3524
Max Act: 5.5711. Min Act: -0.1700
Data Index: 4035618 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3524. Min Range: -6.3524
Max Act: 5.5711. Min Act: -0.1700
Data Index: 338993 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3524. Min Range: -6.3524
Max Act: 5.5711. Min Act: -0.1700
Data Index: 2647439 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3524. Min Range: -6.3524
Max Act: 5.5399. Min Act: -0.1700
Data Index: 6349311 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3524. Min Range: -6.3524
Max Act: 5.5399. Min Act: -0.1700
Data Index: 7890131 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3524. Min Range: -6.3524
Max Act: 5.5399. Min Act: -0.1700
Data Index: 3414718 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3524. Min Range: -6.3524
Max Act: 5.5086. Min Act: -0.1700
Data Index: 2933790 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3524. Min Range: -6.3524
Max Act: 5.5399. Min Act: -0.1700
Data Index: 4446326 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3524. Min Range: -6.3524
Max Act: 5.5086. Min Act: -0.1700
Data Index: 2727575 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3524. Min Range: -6.3524
Max Act: 5.4461. Min Act: -0.1700
Data Index: 2258291 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19