Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1607 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0892. Min Range: -9.0892
Max Act: 9.0892. Min Act: -0.1700
Data Index: 6113035 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.9642. Min Act: -0.1700
Data Index: 3013742 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.8392. Min Act: -0.1700
Data Index: 5307528 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.9017. Min Act: -0.1700
Data Index: 6854984 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.8392. Min Act: -0.1700
Data Index: 4585510 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.7142. Min Act: -0.1700
Data Index: 1614910 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.6517. Min Act: -0.1700
Data Index: 2084294 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.6517. Min Act: -0.1700
Data Index: 22039 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.5892. Min Act: -0.1700
Data Index: 717005 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.5892. Min Act: -0.1700
Data Index: 4899941 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.5267. Min Act: -0.1700
Data Index: 1968902 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.5892. Min Act: -0.1700
Data Index: 7191261 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.5267. Min Act: -0.1700
Data Index: 5554416 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.5267. Min Act: -0.1700
Data Index: 4989133 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.5267. Min Act: -0.1700
Data Index: 2306535 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.5267. Min Act: -0.1700
Data Index: 1361715 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.5267. Min Act: -0.1700
Data Index: 8149508 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.5267. Min Act: -0.1700
Data Index: 5702443 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.5267. Min Act: -0.1700
Data Index: 8006440 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.4642. Min Act: -0.1700
Data Index: 7315435 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19