Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3656 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.8646. Min Act: -0.1700
Data Index: 224023 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.8020. Min Act: -0.1700
Data Index: 5912947 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.7395. Min Act: -0.1700
Data Index: 2885082 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.7082. Min Act: -0.1700
Data Index: 7529626 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.6769. Min Act: -0.1700
Data Index: 7268680 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.6456. Min Act: -0.1700
Data Index: 2632556 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.6456. Min Act: -0.1700
Data Index: 4277148 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.6769. Min Act: -0.1700
Data Index: 5434732 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.5830. Min Act: -0.1700
Data Index: 8163067 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.5517. Min Act: -0.1700
Data Index: 3063817 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.5517. Min Act: -0.1700
Data Index: 8015826 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.5830. Min Act: -0.1700
Data Index: 6985685 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.5517. Min Act: -0.1700
Data Index: 3792658 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.5204. Min Act: -0.1700
Data Index: 36113 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.5204. Min Act: -0.1700
Data Index: 7178990 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.5204. Min Act: -0.1700
Data Index: 387110 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.4577. Min Act: -0.1700
Data Index: 929009 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.4577. Min Act: -0.1700
Data Index: 4066291 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.4577. Min Act: -0.1700
Data Index: 686910 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8646. Min Range: -3.8646
Max Act: 3.4891. Min Act: -0.1700
Data Index: 1896559 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19