Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1269 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2882. Min Act: -0.1700
Data Index: 1059282 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.3196. Min Act: -0.1700
Data Index: 7273269 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.3196. Min Act: -0.1700
Data Index: 2883304 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.3196. Min Act: -0.1700
Data Index: 7641083 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.3196. Min Act: -0.1700
Data Index: 2883302 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2882. Min Act: -0.1700
Data Index: 214114 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2882. Min Act: -0.1700
Data Index: 2813599 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2882. Min Act: -0.1700
Data Index: 506141 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2725. Min Act: -0.1700
Data Index: 1712392 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2725. Min Act: -0.1700
Data Index: 2883303 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 6477451 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 2893338 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 6003444 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 2040795 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2411. Min Act: -0.1700
Data Index: 713854 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 2829968 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 3815383 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2725. Min Act: -0.1700
Data Index: 2449163 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2568. Min Act: -0.1700
Data Index: 2084035 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3196. Min Range: -3.3196
Max Act: 3.2254. Min Act: -0.1700
Data Index: 3568086 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19