Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1577 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.7865. Min Act: -0.1699
Data Index: 2778036 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.5990. Min Act: -0.1700
Data Index: 7379901 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.5678. Min Act: -0.1700
Data Index: 195968 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.5678. Min Act: -0.1700
Data Index: 4872622 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.5053. Min Act: -0.1700
Data Index: 3353906 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.5053. Min Act: -0.1700
Data Index: 8719600 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.4740. Min Act: -0.1700
Data Index: 1632676 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.4115. Min Act: -0.1700
Data Index: 7101484 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.4115. Min Act: -0.1700
Data Index: 6504624 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.4428. Min Act: -0.1700
Data Index: 5758828 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.4115. Min Act: -0.1700
Data Index: 8088391 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.4115. Min Act: -0.1700
Data Index: 2859779 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.3803. Min Act: -0.1700
Data Index: 7243720 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.3803. Min Act: -0.1700
Data Index: 6705628 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.3490. Min Act: -0.1700
Data Index: 8088393 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.3178. Min Act: -0.1700
Data Index: 2782550 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.2865. Min Act: -0.1700
Data Index: 8088392 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.3178. Min Act: -0.1700
Data Index: 2910309 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.2865. Min Act: -0.1700
Data Index: 8366505 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7865. Min Range: -7.7865
Max Act: 7.3178. Min Act: -0.1700
Data Index: 8832327 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19