Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3505 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.7368. Min Act: -0.1700
Data Index: 7620699 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.7681. Min Act: -0.1700
Data Index: 6719669 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.7368. Min Act: -0.1700
Data Index: 6802086 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.7368. Min Act: -0.1700
Data Index: 8137508 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.6899. Min Act: -0.1700
Data Index: 4418672 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.6899. Min Act: -0.1700
Data Index: 6950701 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.6430. Min Act: -0.1700
Data Index: 7997760 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.6273. Min Act: -0.1700
Data Index: 2600183 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.6273. Min Act: -0.1700
Data Index: 8319647 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.6273. Min Act: -0.1700
Data Index: 2449116 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.5960. Min Act: -0.1700
Data Index: 6774091 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.5804. Min Act: -0.1700
Data Index: 3099863 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.5804. Min Act: -0.1700
Data Index: 3462274 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.5647. Min Act: -0.1700
Data Index: 2202404 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.5490. Min Act: -0.1700
Data Index: 5572829 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.5490. Min Act: -0.1700
Data Index: 6724422 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.5490. Min Act: -0.1700
Data Index: 2082610 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.5334. Min Act: -0.1700
Data Index: 5881043 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.5334. Min Act: -0.1700
Data Index: 1137704 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7681. Min Range: -3.7681
Max Act: 3.5334. Min Act: -0.1700
Data Index: 6914682 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19