Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4790 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0344. Min Range: -5.0344
Max Act: 5.0344. Min Act: -0.1700
Data Index: 3013400 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0344. Min Range: -5.0344
Max Act: 4.9406. Min Act: -0.1700
Data Index: 1912180 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0344. Min Range: -5.0344
Max Act: 4.9094. Min Act: -0.1700
Data Index: 219434 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0344. Min Range: -5.0344
Max Act: 4.8156. Min Act: -0.1700
Data Index: 4082370 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0344. Min Range: -5.0344
Max Act: 4.8156. Min Act: -0.1700
Data Index: 219435 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0344. Min Range: -5.0344
Max Act: 4.7844. Min Act: -0.1700
Data Index: 5386455 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0344. Min Range: -5.0344
Max Act: 4.7844. Min Act: -0.1700
Data Index: 7123714 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0344. Min Range: -5.0344
Max Act: 4.7531. Min Act: -0.1700
Data Index: 120490 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0344. Min Range: -5.0344
Max Act: 4.7219. Min Act: -0.1700
Data Index: 2919776 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0344. Min Range: -5.0344
Max Act: 4.7219. Min Act: -0.1700
Data Index: 7488224 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0344. Min Range: -5.0344
Max Act: 4.7219. Min Act: -0.1700
Data Index: 6330752 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0344. Min Range: -5.0344
Max Act: 4.6906. Min Act: -0.1700
Data Index: 8685383 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0344. Min Range: -5.0344
Max Act: 4.6594. Min Act: -0.1700
Data Index: 8355129 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0344. Min Range: -5.0344
Max Act: 4.6906. Min Act: -0.1700
Data Index: 1363692 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0344. Min Range: -5.0344
Max Act: 4.6906. Min Act: -0.1700
Data Index: 3806 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0344. Min Range: -5.0344
Max Act: 4.6594. Min Act: -0.1700
Data Index: 3869094 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0344. Min Range: -5.0344
Max Act: 4.6906. Min Act: -0.1700
Data Index: 6228197 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0344. Min Range: -5.0344
Max Act: 4.6594. Min Act: -0.1700
Data Index: 2463559 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0344. Min Range: -5.0344
Max Act: 4.6594. Min Act: -0.1700
Data Index: 3952228 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0344. Min Range: -5.0344
Max Act: 4.6281. Min Act: -0.1700
Data Index: 7785572 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19