Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3776 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0696. Min Range: -6.0696
Max Act: 6.0696. Min Act: -0.1700
Data Index: 359109 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0696. Min Range: -6.0696
Max Act: 5.7571. Min Act: -0.1700
Data Index: 5466528 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0696. Min Range: -6.0696
Max Act: 5.2884. Min Act: -0.1700
Data Index: 5566529 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0696. Min Range: -6.0696
Max Act: 5.0696. Min Act: -0.1700
Data Index: 5927175 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0696. Min Range: -6.0696
Max Act: 5.0384. Min Act: -0.1700
Data Index: 7703978 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0696. Min Range: -6.0696
Max Act: 5.0384. Min Act: -0.1700
Data Index: 5153089 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0696. Min Range: -6.0696
Max Act: 5.0696. Min Act: -0.1700
Data Index: 8330492 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0696. Min Range: -6.0696
Max Act: 5.0384. Min Act: -0.1700
Data Index: 826444 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0696. Min Range: -6.0696
Max Act: 5.0071. Min Act: -0.1700
Data Index: 3026028 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0696. Min Range: -6.0696
Max Act: 4.9759. Min Act: -0.1700
Data Index: 6794376 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0696. Min Range: -6.0696
Max Act: 4.9759. Min Act: -0.1700
Data Index: 5743914 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0696. Min Range: -6.0696
Max Act: 4.9446. Min Act: -0.1700
Data Index: 2699767 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0696. Min Range: -6.0696
Max Act: 4.9134. Min Act: -0.1700
Data Index: 3577066 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0696. Min Range: -6.0696
Max Act: 4.9446. Min Act: -0.1700
Data Index: 8269864 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0696. Min Range: -6.0696
Max Act: 4.9446. Min Act: -0.1700
Data Index: 6810190 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0696. Min Range: -6.0696
Max Act: 4.9446. Min Act: -0.1700
Data Index: 4351164 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0696. Min Range: -6.0696
Max Act: 4.9134. Min Act: -0.1700
Data Index: 7460368 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0696. Min Range: -6.0696
Max Act: 4.9134. Min Act: -0.1700
Data Index: 2633803 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0696. Min Range: -6.0696
Max Act: 4.9134. Min Act: -0.1700
Data Index: 4405801 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0696. Min Range: -6.0696
Max Act: 4.9134. Min Act: -0.1700
Data Index: 5829725 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19