Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3463 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6098. Min Range: -6.6098
Max Act: 6.6098. Min Act: -0.1700
Data Index: 1386855 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6098. Min Range: -6.6098
Max Act: 6.2348. Min Act: -0.1700
Data Index: 8738936 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6098. Min Range: -6.6098
Max Act: 6.1723. Min Act: -0.1700
Data Index: 7670495 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6098. Min Range: -6.6098
Max Act: 5.9223. Min Act: -0.1700
Data Index: 3148727 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6098. Min Range: -6.6098
Max Act: 5.8598. Min Act: -0.1700
Data Index: 501780 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6098. Min Range: -6.6098
Max Act: 5.8598. Min Act: -0.1700
Data Index: 5454131 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6098. Min Range: -6.6098
Max Act: 5.7973. Min Act: -0.1700
Data Index: 1536477 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6098. Min Range: -6.6098
Max Act: 5.7660. Min Act: -0.1700
Data Index: 7277642 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6098. Min Range: -6.6098
Max Act: 5.7348. Min Act: -0.1700
Data Index: 5177761 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6098. Min Range: -6.6098
Max Act: 5.7348. Min Act: -0.1700
Data Index: 773738 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6098. Min Range: -6.6098
Max Act: 5.6410. Min Act: -0.1700
Data Index: 1853931 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6098. Min Range: -6.6098
Max Act: 5.6410. Min Act: -0.1700
Data Index: 8374348 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6098. Min Range: -6.6098
Max Act: 5.6410. Min Act: -0.1700
Data Index: 7484580 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6098. Min Range: -6.6098
Max Act: 5.6098. Min Act: -0.1700
Data Index: 6826627 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6098. Min Range: -6.6098
Max Act: 5.5785. Min Act: -0.1700
Data Index: 5192613 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6098. Min Range: -6.6098
Max Act: 5.5473. Min Act: -0.1700
Data Index: 1469472 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6098. Min Range: -6.6098
Max Act: 5.5785. Min Act: -0.1700
Data Index: 2495406 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6098. Min Range: -6.6098
Max Act: 5.5160. Min Act: -0.1700
Data Index: 5364438 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6098. Min Range: -6.6098
Max Act: 5.5160. Min Act: -0.1700
Data Index: 1177372 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6098. Min Range: -6.6098
Max Act: 5.5160. Min Act: -0.1700
Data Index: 1966457 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19