Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3864 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4254. Min Range: -5.4254
Max Act: 5.4254. Min Act: -0.1700
Data Index: 3395616 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4254. Min Range: -5.4254
Max Act: 5.3941. Min Act: -0.1700
Data Index: 4538768 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4254. Min Range: -5.4254
Max Act: 5.3316. Min Act: -0.1700
Data Index: 5314449 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4254. Min Range: -5.4254
Max Act: 5.3316. Min Act: -0.1700
Data Index: 8801273 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4254. Min Range: -5.4254
Max Act: 5.2379. Min Act: -0.1700
Data Index: 7484371 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4254. Min Range: -5.4254
Max Act: 5.1754. Min Act: -0.1700
Data Index: 3701232 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4254. Min Range: -5.4254
Max Act: 5.1754. Min Act: -0.1700
Data Index: 5417286 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4254. Min Range: -5.4254
Max Act: 5.2066. Min Act: -0.1700
Data Index: 8182726 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4254. Min Range: -5.4254
Max Act: 5.2066. Min Act: -0.1700
Data Index: 1630230 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4254. Min Range: -5.4254
Max Act: 5.1441. Min Act: -0.1700
Data Index: 8401220 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4254. Min Range: -5.4254
Max Act: 5.1754. Min Act: -0.1700
Data Index: 6762731 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4254. Min Range: -5.4254
Max Act: 5.1754. Min Act: -0.1700
Data Index: 6541462 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4254. Min Range: -5.4254
Max Act: 5.1441. Min Act: -0.1700
Data Index: 2428086 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4254. Min Range: -5.4254
Max Act: 5.1129. Min Act: -0.1700
Data Index: 1831566 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4254. Min Range: -5.4254
Max Act: 5.0816. Min Act: -0.1700
Data Index: 2242538 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4254. Min Range: -5.4254
Max Act: 5.0816. Min Act: -0.1700
Data Index: 7296120 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4254. Min Range: -5.4254
Max Act: 5.0816. Min Act: -0.1700
Data Index: 778482 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4254. Min Range: -5.4254
Max Act: 5.0191. Min Act: -0.1700
Data Index: 7443887 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4254. Min Range: -5.4254
Max Act: 4.9879. Min Act: -0.1700
Data Index: 5155756 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4254. Min Range: -5.4254
Max Act: 5.0191. Min Act: -0.1700
Data Index: 118359 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19