Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6366 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.9866. Min Act: -0.1700
Data Index: 7823485 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.9866. Min Act: -0.1700
Data Index: 6659386 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.6428. Min Act: -0.1700
Data Index: 4492333 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.6428. Min Act: -0.1700
Data Index: 6268674 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.6428. Min Act: -0.1700
Data Index: 4492331 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.6116. Min Act: -0.1700
Data Index: 5236927 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.5803. Min Act: -0.1700
Data Index: 1154316 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.5803. Min Act: -0.1700
Data Index: 6679945 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.5491. Min Act: -0.1700
Data Index: 7909414 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.5491. Min Act: -0.1700
Data Index: 1082856 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.5491. Min Act: -0.1700
Data Index: 7610383 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.5178. Min Act: -0.1700
Data Index: 8329046 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.4866. Min Act: -0.1700
Data Index: 1304034 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.4553. Min Act: -0.1700
Data Index: 138950 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.3928. Min Act: -0.1700
Data Index: 2403931 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.4241. Min Act: -0.1700
Data Index: 1880106 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.4241. Min Act: -0.1700
Data Index: 3109508 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.3616. Min Act: -0.1700
Data Index: 7731074 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.3303. Min Act: -0.1700
Data Index: 5230170 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9866. Min Range: -6.9866
Max Act: 6.3303. Min Act: -0.1700
Data Index: 5307177 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19