Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4965 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.8221. Min Act: -0.1700
Data Index: 8278296 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.6659. Min Act: -0.1700
Data Index: 1347953 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.5721. Min Act: -0.1700
Data Index: 8687088 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.5721. Min Act: -0.1700
Data Index: 206883 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.5721. Min Act: -0.1700
Data Index: 8145648 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.5409. Min Act: -0.1700
Data Index: 5320749 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.5096. Min Act: -0.1700
Data Index: 3659508 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.5096. Min Act: -0.1700
Data Index: 3340022 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.4784. Min Act: -0.1700
Data Index: 5160535 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.4784. Min Act: -0.1700
Data Index: 6301596 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.4784. Min Act: -0.1700
Data Index: 7553465 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.4471. Min Act: -0.1700
Data Index: 8212096 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.4784. Min Act: -0.1700
Data Index: 1993100 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.4159. Min Act: -0.1700
Data Index: 4377171 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.4159. Min Act: -0.1700
Data Index: 3759285 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.4159. Min Act: -0.1700
Data Index: 5089454 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.3846. Min Act: -0.1700
Data Index: 5624363 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.3846. Min Act: -0.1700
Data Index: 6575994 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.3846. Min Act: -0.1700
Data Index: 4328773 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8221. Min Range: -5.8221
Max Act: 5.3221. Min Act: -0.1700
Data Index: 1135953 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19