Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 996 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.5545. Min Act: -0.1700
Data Index: 5106951 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.4762. Min Act: -0.1700
Data Index: 5949600 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.4292. Min Act: -0.1700
Data Index: 2456319 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.4292. Min Act: -0.1700
Data Index: 4500844 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.4135. Min Act: -0.1700
Data Index: 8511156 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.3978. Min Act: -0.1700
Data Index: 6453546 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.3978. Min Act: -0.1700
Data Index: 7095918 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.3978. Min Act: -0.1700
Data Index: 1535184 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.3978. Min Act: -0.1700
Data Index: 8447318 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.3665. Min Act: -0.1700
Data Index: 5063804 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.3665. Min Act: -0.1700
Data Index: 6920986 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.3665. Min Act: -0.1700
Data Index: 4459442 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.3665. Min Act: -0.1700
Data Index: 544365 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.3665. Min Act: -0.1700
Data Index: 8417638 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.3508. Min Act: -0.1700
Data Index: 1735229 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.3351. Min Act: -0.1700
Data Index: 8089582 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.3351. Min Act: -0.1700
Data Index: 3768048 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.3194. Min Act: -0.1700
Data Index: 2676884 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.3351. Min Act: -0.1700
Data Index: 1541913 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5545. Min Range: -3.5545
Max Act: 3.3351. Min Act: -0.1700
Data Index: 5986426 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19