Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3620 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.9348. Min Act: -0.1700
Data Index: 5646500 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.8723. Min Act: -0.1700
Data Index: 5237594 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.8411. Min Act: -0.1700
Data Index: 8023646 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.8098. Min Act: -0.1700
Data Index: 325061 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.7786. Min Act: -0.1700
Data Index: 7112109 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.7473. Min Act: -0.1700
Data Index: 1641990 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.7473. Min Act: -0.1700
Data Index: 2860493 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.7786. Min Act: -0.1700
Data Index: 1685534 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.7161. Min Act: -0.1700
Data Index: 6827105 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.6848. Min Act: -0.1700
Data Index: 6025652 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.6848. Min Act: -0.1700
Data Index: 3990984 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.6223. Min Act: -0.1700
Data Index: 6292453 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.6223. Min Act: -0.1700
Data Index: 8095747 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.5911. Min Act: -0.1700
Data Index: 1159350 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.5911. Min Act: -0.1700
Data Index: 7224445 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.5598. Min Act: -0.1700
Data Index: 1674500 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.5598. Min Act: -0.1700
Data Index: 6288924 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.5598. Min Act: -0.1700
Data Index: 3222379 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.4973. Min Act: -0.1700
Data Index: 997387 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9348. Min Range: -5.9348
Max Act: 5.4973. Min Act: -0.1700
Data Index: 2247309 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19