Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7670. Min Range: -7.7670
Max Act: 7.7670. Min Act: -0.1700
Data Index: 8637643 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7670. Min Range: -7.7670
Max Act: 7.2357. Min Act: -0.1700
Data Index: 1977430 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7670. Min Range: -7.7670
Max Act: 6.8920. Min Act: -0.1700
Data Index: 8311052 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7670. Min Range: -7.7670
Max Act: 6.8295. Min Act: -0.1700
Data Index: 2726406 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7670. Min Range: -7.7670
Max Act: 6.7670. Min Act: -0.1700
Data Index: 8474645 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7670. Min Range: -7.7670
Max Act: 6.7357. Min Act: -0.1700
Data Index: 6825704 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7670. Min Range: -7.7670
Max Act: 6.6732. Min Act: -0.1700
Data Index: 1098239 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7670. Min Range: -7.7670
Max Act: 6.6732. Min Act: -0.1700
Data Index: 7271423 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7670. Min Range: -7.7670
Max Act: 6.5482. Min Act: -0.1700
Data Index: 1085814 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7670. Min Range: -7.7670
Max Act: 6.5170. Min Act: -0.1700
Data Index: 599209 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7670. Min Range: -7.7670
Max Act: 6.4857. Min Act: -0.1700
Data Index: 5428952 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7670. Min Range: -7.7670
Max Act: 6.4545. Min Act: -0.1700
Data Index: 4124575 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7670. Min Range: -7.7670
Max Act: 6.4545. Min Act: -0.1700
Data Index: 4228507 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7670. Min Range: -7.7670
Max Act: 6.4545. Min Act: -0.1700
Data Index: 5500631 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7670. Min Range: -7.7670
Max Act: 6.4232. Min Act: -0.1700
Data Index: 455188 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7670. Min Range: -7.7670
Max Act: 6.4232. Min Act: -0.1700
Data Index: 1898657 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7670. Min Range: -7.7670
Max Act: 6.4232. Min Act: -0.1700
Data Index: 5409802 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7670. Min Range: -7.7670
Max Act: 6.3607. Min Act: -0.1700
Data Index: 2153854 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7670. Min Range: -7.7670
Max Act: 6.3920. Min Act: -0.1700
Data Index: 2115938 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7670. Min Range: -7.7670
Max Act: 6.3607. Min Act: -0.1700
Data Index: 554833 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19