Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 564 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6191. Min Range: -6.6191
Max Act: 6.6191. Min Act: -0.1700
Data Index: 5470382 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6191. Min Range: -6.6191
Max Act: 6.4316. Min Act: -0.1700
Data Index: 240386 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6191. Min Range: -6.6191
Max Act: 6.3066. Min Act: -0.1700
Data Index: 2760370 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6191. Min Range: -6.6191
Max Act: 6.3066. Min Act: -0.1700
Data Index: 196063 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6191. Min Range: -6.6191
Max Act: 6.3066. Min Act: -0.1700
Data Index: 1752615 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6191. Min Range: -6.6191
Max Act: 6.2441. Min Act: -0.1700
Data Index: 247791 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6191. Min Range: -6.6191
Max Act: 6.1191. Min Act: -0.1700
Data Index: 2568160 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6191. Min Range: -6.6191
Max Act: 6.1191. Min Act: -0.1700
Data Index: 6019894 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6191. Min Range: -6.6191
Max Act: 6.1191. Min Act: -0.1700
Data Index: 241594 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6191. Min Range: -6.6191
Max Act: 6.0879. Min Act: -0.1700
Data Index: 6715545 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6191. Min Range: -6.6191
Max Act: 6.0566. Min Act: -0.1700
Data Index: 7123580 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6191. Min Range: -6.6191
Max Act: 6.0566. Min Act: -0.1700
Data Index: 2517496 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6191. Min Range: -6.6191
Max Act: 6.0566. Min Act: -0.1700
Data Index: 599676 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6191. Min Range: -6.6191
Max Act: 6.0566. Min Act: -0.1700
Data Index: 4554156 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6191. Min Range: -6.6191
Max Act: 6.0254. Min Act: -0.1700
Data Index: 7347445 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6191. Min Range: -6.6191
Max Act: 5.9941. Min Act: -0.1700
Data Index: 6928275 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6191. Min Range: -6.6191
Max Act: 5.9941. Min Act: -0.1700
Data Index: 656016 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6191. Min Range: -6.6191
Max Act: 5.9941. Min Act: -0.1700
Data Index: 1554382 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6191. Min Range: -6.6191
Max Act: 5.9629. Min Act: -0.1700
Data Index: 2960586 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6191. Min Range: -6.6191
Max Act: 5.9941. Min Act: -0.1700
Data Index: 4490946 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19