Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4006 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0158. Min Range: -7.0158
Max Act: 7.0158. Min Act: -0.1700
Data Index: 5699187 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0158. Min Range: -7.0158
Max Act: 6.7033. Min Act: -0.1695
Data Index: 4039356 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0158. Min Range: -7.0158
Max Act: 6.7658. Min Act: -0.1700
Data Index: 135697 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0158. Min Range: -7.0158
Max Act: 6.6720. Min Act: -0.1700
Data Index: 7863747 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0158. Min Range: -7.0158
Max Act: 6.6408. Min Act: -0.1700
Data Index: 6040365 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0158. Min Range: -7.0158
Max Act: 6.6720. Min Act: -0.1700
Data Index: 6244466 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0158. Min Range: -7.0158
Max Act: 6.6408. Min Act: -0.1700
Data Index: 4862788 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0158. Min Range: -7.0158
Max Act: 6.6095. Min Act: -0.1699
Data Index: 4039353 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0158. Min Range: -7.0158
Max Act: 6.6095. Min Act: -0.1700
Data Index: 3213487 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0158. Min Range: -7.0158
Max Act: 6.5783. Min Act: -0.1700
Data Index: 7939996 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0158. Min Range: -7.0158
Max Act: 6.5783. Min Act: -0.1700
Data Index: 6566485 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0158. Min Range: -7.0158
Max Act: 6.5783. Min Act: -0.1700
Data Index: 7295782 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0158. Min Range: -7.0158
Max Act: 6.5158. Min Act: -0.1700
Data Index: 78010 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0158. Min Range: -7.0158
Max Act: 6.4845. Min Act: -0.1700
Data Index: 1605464 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0158. Min Range: -7.0158
Max Act: 6.4845. Min Act: -0.1700
Data Index: 1174839 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0158. Min Range: -7.0158
Max Act: 6.4533. Min Act: -0.1700
Data Index: 5340349 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0158. Min Range: -7.0158
Max Act: 6.4533. Min Act: -0.1700
Data Index: 8195179 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0158. Min Range: -7.0158
Max Act: 6.4533. Min Act: -0.1700
Data Index: 6149240 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0158. Min Range: -7.0158
Max Act: 6.4220. Min Act: -0.1700
Data Index: 1681368 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0158. Min Range: -7.0158
Max Act: 6.4533. Min Act: -0.1700
Data Index: 5466356 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19