Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3857 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4442. Min Range: -6.4442
Max Act: 6.4442. Min Act: -0.1700
Data Index: 829375 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4442. Min Range: -6.4442
Max Act: 6.2567. Min Act: -0.1700
Data Index: 8083391 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4442. Min Range: -6.4442
Max Act: 6.2567. Min Act: -0.1700
Data Index: 5949866 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4442. Min Range: -6.4442
Max Act: 6.1942. Min Act: -0.1700
Data Index: 873296 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4442. Min Range: -6.4442
Max Act: 6.1942. Min Act: -0.1700
Data Index: 5888284 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4442. Min Range: -6.4442
Max Act: 6.1005. Min Act: -0.1700
Data Index: 7625152 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4442. Min Range: -6.4442
Max Act: 6.1005. Min Act: -0.1700
Data Index: 7993332 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4442. Min Range: -6.4442
Max Act: 6.1005. Min Act: -0.1700
Data Index: 5362535 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4442. Min Range: -6.4442
Max Act: 6.0692. Min Act: -0.1700
Data Index: 4961397 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4442. Min Range: -6.4442
Max Act: 6.0380. Min Act: -0.1700
Data Index: 1105617 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4442. Min Range: -6.4442
Max Act: 6.0380. Min Act: -0.1700
Data Index: 2709631 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4442. Min Range: -6.4442
Max Act: 5.9755. Min Act: -0.1700
Data Index: 5667293 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4442. Min Range: -6.4442
Max Act: 5.9442. Min Act: -0.1700
Data Index: 8548077 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4442. Min Range: -6.4442
Max Act: 5.9442. Min Act: -0.1700
Data Index: 1083154 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4442. Min Range: -6.4442
Max Act: 5.9442. Min Act: -0.1700
Data Index: 6381163 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4442. Min Range: -6.4442
Max Act: 5.9442. Min Act: -0.1700
Data Index: 5162715 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4442. Min Range: -6.4442
Max Act: 5.9442. Min Act: -0.1700
Data Index: 6309526 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4442. Min Range: -6.4442
Max Act: 5.9442. Min Act: -0.1700
Data Index: 6212198 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4442. Min Range: -6.4442
Max Act: 5.9442. Min Act: -0.1700
Data Index: 2102662 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4442. Min Range: -6.4442
Max Act: 5.8817. Min Act: -0.1700
Data Index: 393400 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19