Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1051 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3291. Min Range: -6.3291
Max Act: 6.3291. Min Act: -0.1700
Data Index: 1850720 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3291. Min Range: -6.3291
Max Act: 6.0791. Min Act: -0.1700
Data Index: 7257692 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3291. Min Range: -6.3291
Max Act: 5.8916. Min Act: -0.1700
Data Index: 2505030 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3291. Min Range: -6.3291
Max Act: 5.8603. Min Act: -0.1700
Data Index: 8131369 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3291. Min Range: -6.3291
Max Act: 5.8291. Min Act: -0.1700
Data Index: 6048977 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3291. Min Range: -6.3291
Max Act: 5.8291. Min Act: -0.1700
Data Index: 847131 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3291. Min Range: -6.3291
Max Act: 5.7666. Min Act: -0.1700
Data Index: 7669664 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3291. Min Range: -6.3291
Max Act: 5.7353. Min Act: -0.1700
Data Index: 7787722 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3291. Min Range: -6.3291
Max Act: 5.7041. Min Act: -0.1700
Data Index: 7629355 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3291. Min Range: -6.3291
Max Act: 5.6728. Min Act: -0.1700
Data Index: 59569 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3291. Min Range: -6.3291
Max Act: 5.6103. Min Act: -0.1700
Data Index: 2044911 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3291. Min Range: -6.3291
Max Act: 5.6103. Min Act: -0.1700
Data Index: 1807852 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3291. Min Range: -6.3291
Max Act: 5.6103. Min Act: -0.1700
Data Index: 1312874 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3291. Min Range: -6.3291
Max Act: 5.5791. Min Act: -0.1700
Data Index: 3078843 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3291. Min Range: -6.3291
Max Act: 5.6103. Min Act: -0.1700
Data Index: 5768365 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3291. Min Range: -6.3291
Max Act: 5.6103. Min Act: -0.1700
Data Index: 6914683 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3291. Min Range: -6.3291
Max Act: 5.6103. Min Act: -0.1700
Data Index: 3393244 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3291. Min Range: -6.3291
Max Act: 5.5791. Min Act: -0.1700
Data Index: 4738021 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3291. Min Range: -6.3291
Max Act: 5.5791. Min Act: -0.1700
Data Index: 3067387 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3291. Min Range: -6.3291
Max Act: 5.5791. Min Act: -0.1700
Data Index: 100859 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19