Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.7265. Min Act: -0.1700
Data Index: 6816555 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.5703. Min Act: -0.1700
Data Index: 2055324 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.4765. Min Act: -0.1700
Data Index: 5541024 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.4453. Min Act: -0.1700
Data Index: 1977890 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.4140. Min Act: -0.1700
Data Index: 4596394 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.3828. Min Act: -0.1700
Data Index: 2390087 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.3828. Min Act: -0.1700
Data Index: 3111784 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.3515. Min Act: -0.1700
Data Index: 6610484 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.3515. Min Act: -0.1700
Data Index: 1855358 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.3203. Min Act: -0.1700
Data Index: 2992966 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.2890. Min Act: -0.1700
Data Index: 2667836 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.2578. Min Act: -0.1700
Data Index: 1018556 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.2890. Min Act: -0.1700
Data Index: 3107916 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.2265. Min Act: -0.1700
Data Index: 3660767 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.2265. Min Act: -0.1700
Data Index: 1183239 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.2265. Min Act: -0.1700
Data Index: 2830104 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.1640. Min Act: -0.1700
Data Index: 4935966 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.1953. Min Act: -0.1700
Data Index: 117253 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.1953. Min Act: -0.1700
Data Index: 8213367 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7265. Min Range: -6.7265
Max Act: 6.1953. Min Act: -0.1700
Data Index: 5608362 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19