Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4408 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.7879. Min Act: -0.1700
Data Index: 1655561 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6316. Min Act: -0.1700
Data Index: 1266334 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6628. Min Act: -0.1700
Data Index: 4376156 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6003. Min Act: -0.1700
Data Index: 3856134 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6003. Min Act: -0.1700
Data Index: 6754685 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5691. Min Act: -0.1700
Data Index: 8474143 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6003. Min Act: -0.1700
Data Index: 8184751 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6003. Min Act: -0.1700
Data Index: 1152779 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5691. Min Act: -0.1700
Data Index: 4627459 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5378. Min Act: -0.1700
Data Index: 4906259 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5691. Min Act: -0.1700
Data Index: 5199953 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5378. Min Act: -0.1700
Data Index: 6677879 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5691. Min Act: -0.1700
Data Index: 2767645 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5378. Min Act: -0.1700
Data Index: 4280783 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5378. Min Act: -0.1700
Data Index: 8720712 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5378. Min Act: -0.1700
Data Index: 959028 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5378. Min Act: -0.1700
Data Index: 2025372 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5378. Min Act: -0.1700
Data Index: 5628478 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.5378. Min Act: -0.1700
Data Index: 7253154 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.4753. Min Act: -0.1700
Data Index: 3494592 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19