Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3332 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.3167. Min Range: -12.3167
Max Act: 12.3167. Min Act: -0.1700
Data Index: 5803461 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3167. Min Range: -12.3167
Max Act: 12.3167. Min Act: -0.1700
Data Index: 6829574 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3167. Min Range: -12.3167
Max Act: 12.2542. Min Act: -0.1700
Data Index: 2163961 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3167. Min Range: -12.3167
Max Act: 12.1292. Min Act: -0.1700
Data Index: 409807 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3167. Min Range: -12.3167
Max Act: 12.0667. Min Act: -0.1700
Data Index: 903563 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3167. Min Range: -12.3167
Max Act: 12.0667. Min Act: -0.1700
Data Index: 4811118 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3167. Min Range: -12.3167
Max Act: 12.0042. Min Act: -0.1700
Data Index: 3200357 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3167. Min Range: -12.3167
Max Act: 12.0042. Min Act: -0.1700
Data Index: 1483129 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3167. Min Range: -12.3167
Max Act: 12.0667. Min Act: -0.1700
Data Index: 1948549 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3167. Min Range: -12.3167
Max Act: 12.0042. Min Act: -0.1700
Data Index: 337492 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3167. Min Range: -12.3167
Max Act: 12.0042. Min Act: -0.1700
Data Index: 3903422 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3167. Min Range: -12.3167
Max Act: 12.0042. Min Act: -0.1700
Data Index: 6332680 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3167. Min Range: -12.3167
Max Act: 12.0042. Min Act: -0.1700
Data Index: 5221659 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3167. Min Range: -12.3167
Max Act: 11.8792. Min Act: -0.1700
Data Index: 143489 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3167. Min Range: -12.3167
Max Act: 11.8792. Min Act: -0.1700
Data Index: 3815961 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3167. Min Range: -12.3167
Max Act: 11.8167. Min Act: -0.1700
Data Index: 6019776 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3167. Min Range: -12.3167
Max Act: 11.8167. Min Act: -0.1700
Data Index: 1907898 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3167. Min Range: -12.3167
Max Act: 11.8167. Min Act: -0.1700
Data Index: 802553 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3167. Min Range: -12.3167
Max Act: 11.8167. Min Act: -0.1700
Data Index: 1405040 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3167. Min Range: -12.3167
Max Act: 11.8167. Min Act: -0.1700
Data Index: 317878 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19