Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 44 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.6690. Min Act: -0.1700
Data Index: 3442321 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.6690. Min Act: -0.1700
Data Index: 3442319 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.5440. Min Act: -0.1700
Data Index: 7908978 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.5128. Min Act: -0.1700
Data Index: 5509842 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.5128. Min Act: -0.1700
Data Index: 6718321 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.4815. Min Act: -0.1700
Data Index: 6708428 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.4815. Min Act: -0.1700
Data Index: 5794167 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.5128. Min Act: -0.1700
Data Index: 7569714 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.4503. Min Act: -0.1700
Data Index: 1648998 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.4503. Min Act: -0.1700
Data Index: 5727003 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.4503. Min Act: -0.1700
Data Index: 89182 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.4503. Min Act: -0.1700
Data Index: 1094859 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.4503. Min Act: -0.1700
Data Index: 8432162 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.4503. Min Act: -0.1700
Data Index: 2779281 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.4503. Min Act: -0.1700
Data Index: 6072551 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.4503. Min Act: -0.1700
Data Index: 1013510 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.4503. Min Act: -0.1700
Data Index: 4698430 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.4190. Min Act: -0.1700
Data Index: 2914661 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.4190. Min Act: -0.1700
Data Index: 5988789 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6690. Min Range: -5.6690
Max Act: 5.3878. Min Act: -0.1700
Data Index: 1013517 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19