Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3265 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0672. Min Range: -2.0672
Max Act: 2.0672. Min Act: -0.1700
Data Index: 7074324 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0672. Min Range: -2.0672
Max Act: 1.9998. Min Act: -0.1700
Data Index: 2610511 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0672. Min Range: -2.0672
Max Act: 1.9829. Min Act: -0.1700
Data Index: 8285563 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0672. Min Range: -2.0672
Max Act: 1.9829. Min Act: -0.1700
Data Index: 1955679 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0672. Min Range: -2.0672
Max Act: 1.9829. Min Act: -0.1700
Data Index: 1796462 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0672. Min Range: -2.0672
Max Act: 1.9829. Min Act: -0.1700
Data Index: 6725816 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0672. Min Range: -2.0672
Max Act: 1.9659. Min Act: -0.1700
Data Index: 6725815 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0672. Min Range: -2.0672
Max Act: 1.9829. Min Act: -0.1700
Data Index: 5079430 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0672. Min Range: -2.0672
Max Act: 1.9829. Min Act: -0.1700
Data Index: 7624374 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0672. Min Range: -2.0672
Max Act: 1.9659. Min Act: -0.1699
Data Index: 8750952 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0672. Min Range: -2.0672
Max Act: 1.9659. Min Act: -0.1700
Data Index: 6665947 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0672. Min Range: -2.0672
Max Act: 1.9659. Min Act: -0.1699
Data Index: 7085326 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0672. Min Range: -2.0672
Max Act: 1.9575. Min Act: -0.1700
Data Index: 8289027 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0672. Min Range: -2.0672
Max Act: 1.9575. Min Act: -0.1700
Data Index: 8041045 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0672. Min Range: -2.0672
Max Act: 1.9575. Min Act: -0.1700
Data Index: 5994638 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0672. Min Range: -2.0672
Max Act: 1.9659. Min Act: -0.1700
Data Index: 893954 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0672. Min Range: -2.0672
Max Act: 1.9575. Min Act: -0.1700
Data Index: 4477643 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0672. Min Range: -2.0672
Max Act: 1.9575. Min Act: -0.1700
Data Index: 8247150 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0672. Min Range: -2.0672
Max Act: 1.9490. Min Act: -0.1700
Data Index: 1034423 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0672. Min Range: -2.0672
Max Act: 1.9575. Min Act: -0.1700
Data Index: 7612543 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19