Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3720 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.4819. Min Act: -0.1700
Data Index: 3327407 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.3722. Min Act: -0.1700
Data Index: 8174189 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.3722. Min Act: -0.1700
Data Index: 4018131 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.3565. Min Act: -0.1700
Data Index: 5204464 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.3251. Min Act: -0.1700
Data Index: 7247032 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.3408. Min Act: -0.1700
Data Index: 7697355 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.3094. Min Act: -0.1700
Data Index: 5097398 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.3251. Min Act: -0.1700
Data Index: 2739576 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.2937. Min Act: -0.1700
Data Index: 1460736 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.2780. Min Act: -0.1700
Data Index: 3341027 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.2623. Min Act: -0.1700
Data Index: 1534796 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.2780. Min Act: -0.1700
Data Index: 2419710 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.2623. Min Act: -0.1700
Data Index: 7697357 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.2466. Min Act: -0.1700
Data Index: 2915932 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.2466. Min Act: -0.1700
Data Index: 4483770 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.2466. Min Act: -0.1700
Data Index: 2086673 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.2309. Min Act: -0.1700
Data Index: 2730698 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.2309. Min Act: -0.1700
Data Index: 7868128 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.2466. Min Act: -0.1700
Data Index: 3849300 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4819. Min Range: -3.4819
Max Act: 3.2309. Min Act: -0.1700
Data Index: 5799425 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19