Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.8230. Min Act: -0.1700
Data Index: 2081881 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.8230. Min Act: -0.1700
Data Index: 1815959 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.8230. Min Act: -0.1700
Data Index: 6124297 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.7917. Min Act: -0.1700
Data Index: 5036087 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.7917. Min Act: -0.1700
Data Index: 6166953 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.7604. Min Act: -0.1700
Data Index: 8032853 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.7291. Min Act: -0.1700
Data Index: 6455091 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.7291. Min Act: -0.1700
Data Index: 7421219 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.7291. Min Act: -0.1700
Data Index: 2428976 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.6978. Min Act: -0.1700
Data Index: 352790 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.6978. Min Act: -0.1700
Data Index: 90185 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.6822. Min Act: -0.1700
Data Index: 7017846 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.6822. Min Act: -0.1700
Data Index: 1375651 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.6666. Min Act: -0.1700
Data Index: 8777233 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.6666. Min Act: -0.1700
Data Index: 6997657 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.6666. Min Act: -0.1700
Data Index: 4524447 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.6509. Min Act: -0.1700
Data Index: 8254694 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.6509. Min Act: -0.1700
Data Index: 6562595 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.6509. Min Act: -0.1700
Data Index: 5874684 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8230. Min Range: -3.8230
Max Act: 3.6353. Min Act: -0.1700
Data Index: 8619330 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19