Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5310 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.8936. Min Act: -0.1700
Data Index: 7015712 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.8311. Min Act: -0.1700
Data Index: 3149376 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.7374. Min Act: -0.1700
Data Index: 5720698 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.5499. Min Act: -0.1700
Data Index: 8647719 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.5499. Min Act: -0.1700
Data Index: 7682340 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.5811. Min Act: -0.1700
Data Index: 6588624 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.5499. Min Act: -0.1700
Data Index: 6272898 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.5499. Min Act: -0.1700
Data Index: 1100588 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.5499. Min Act: -0.1700
Data Index: 7254809 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.5499. Min Act: -0.1700
Data Index: 3667797 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.5499. Min Act: -0.1700
Data Index: 4783437 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.5186. Min Act: -0.1700
Data Index: 975010 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.5186. Min Act: -0.1700
Data Index: 2700382 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.4874. Min Act: -0.1700
Data Index: 2344440 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.4874. Min Act: -0.1700
Data Index: 5778274 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.4874. Min Act: -0.1700
Data Index: 6264704 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.4249. Min Act: -0.1700
Data Index: 6622786 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.4561. Min Act: -0.1700
Data Index: 7172646 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.4561. Min Act: -0.1700
Data Index: 6318477 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8936. Min Range: -4.8936
Max Act: 4.4561. Min Act: -0.1700
Data Index: 5682747 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19