Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 506 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0286. Min Range: -7.0286
Max Act: 7.0286. Min Act: -0.1700
Data Index: 2513578 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0286. Min Range: -7.0286
Max Act: 6.7786. Min Act: -0.1700
Data Index: 1676260 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0286. Min Range: -7.0286
Max Act: 6.7473. Min Act: -0.1700
Data Index: 1726506 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0286. Min Range: -7.0286
Max Act: 6.6848. Min Act: -0.1700
Data Index: 8822566 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0286. Min Range: -7.0286
Max Act: 6.6848. Min Act: -0.1700
Data Index: 5170354 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0286. Min Range: -7.0286
Max Act: 6.6536. Min Act: -0.1700
Data Index: 7850192 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0286. Min Range: -7.0286
Max Act: 6.6223. Min Act: -0.1700
Data Index: 337288 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0286. Min Range: -7.0286
Max Act: 6.6223. Min Act: -0.1700
Data Index: 2092472 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0286. Min Range: -7.0286
Max Act: 6.6223. Min Act: -0.1700
Data Index: 2990914 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0286. Min Range: -7.0286
Max Act: 6.5598. Min Act: -0.1700
Data Index: 7056795 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0286. Min Range: -7.0286
Max Act: 6.5286. Min Act: -0.1700
Data Index: 4897591 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0286. Min Range: -7.0286
Max Act: 6.5598. Min Act: -0.1700
Data Index: 7006300 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0286. Min Range: -7.0286
Max Act: 6.5598. Min Act: -0.1700
Data Index: 4174506 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0286. Min Range: -7.0286
Max Act: 6.5598. Min Act: -0.1700
Data Index: 1322332 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0286. Min Range: -7.0286
Max Act: 6.5286. Min Act: -0.1700
Data Index: 4835036 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0286. Min Range: -7.0286
Max Act: 6.4973. Min Act: -0.1700
Data Index: 3601104 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0286. Min Range: -7.0286
Max Act: 6.4661. Min Act: -0.1700
Data Index: 5132449 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0286. Min Range: -7.0286
Max Act: 6.4348. Min Act: -0.1700
Data Index: 5839271 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0286. Min Range: -7.0286
Max Act: 6.4348. Min Act: -0.1700
Data Index: 3572910 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0286. Min Range: -7.0286
Max Act: 6.4348. Min Act: -0.1700
Data Index: 2405121 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19