Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4746 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6327. Min Range: -9.6327
Max Act: 9.6327. Min Act: -0.1700
Data Index: 7735381 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6327. Min Range: -9.6327
Max Act: 9.3202. Min Act: -0.1700
Data Index: 4029685 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6327. Min Range: -9.6327
Max Act: 9.1327. Min Act: -0.1700
Data Index: 6337788 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6327. Min Range: -9.6327
Max Act: 9.0077. Min Act: -0.1700
Data Index: 5987966 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6327. Min Range: -9.6327
Max Act: 9.0077. Min Act: -0.1700
Data Index: 6355488 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6327. Min Range: -9.6327
Max Act: 9.0077. Min Act: -0.1700
Data Index: 5309800 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6327. Min Range: -9.6327
Max Act: 9.0077. Min Act: -0.1700
Data Index: 6323432 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6327. Min Range: -9.6327
Max Act: 8.7577. Min Act: -0.1700
Data Index: 4029679 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6327. Min Range: -9.6327
Max Act: 8.8202. Min Act: -0.1700
Data Index: 6330662 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6327. Min Range: -9.6327
Max Act: 8.7577. Min Act: -0.1700
Data Index: 1678642 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6327. Min Range: -9.6327
Max Act: 8.7577. Min Act: -0.1700
Data Index: 3857006 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6327. Min Range: -9.6327
Max Act: 8.7577. Min Act: -0.1700
Data Index: 7735379 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6327. Min Range: -9.6327
Max Act: 8.6952. Min Act: -0.1700
Data Index: 7735382 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6327. Min Range: -9.6327
Max Act: 8.6327. Min Act: -0.1700
Data Index: 4237878 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6327. Min Range: -9.6327
Max Act: 8.6952. Min Act: -0.1700
Data Index: 6099324 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6327. Min Range: -9.6327
Max Act: 8.6952. Min Act: -0.1700
Data Index: 4029688 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6327. Min Range: -9.6327
Max Act: 8.6952. Min Act: -0.1700
Data Index: 7394497 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6327. Min Range: -9.6327
Max Act: 8.5702. Min Act: -0.1700
Data Index: 7926561 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6327. Min Range: -9.6327
Max Act: 8.6327. Min Act: -0.1700
Data Index: 8693171 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6327. Min Range: -9.6327
Max Act: 8.6327. Min Act: -0.1700
Data Index: 581369 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19