Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1145 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.6566. Min Act: -0.1547
Data Index: 681044 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.4379. Min Act: -0.1700
Data Index: 369904 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.5316. Min Act: -0.1700
Data Index: 5016049 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.5004. Min Act: -0.1700
Data Index: 8151936 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.4691. Min Act: -0.1700
Data Index: 779844 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.4379. Min Act: -0.1700
Data Index: 737116 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.4066. Min Act: -0.1700
Data Index: 677082 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.4066. Min Act: -0.1700
Data Index: 5955475 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.3441. Min Act: -0.1700
Data Index: 1991795 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.2816. Min Act: -0.1700
Data Index: 6468897 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.2191. Min Act: -0.1700
Data Index: 5401905 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.2816. Min Act: -0.1700
Data Index: 2026496 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.2816. Min Act: -0.1700
Data Index: 6742392 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.1879. Min Act: -0.1700
Data Index: 2212349 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.2191. Min Act: -0.1700
Data Index: 3192787 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.1879. Min Act: -0.1700
Data Index: 8555116 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.1254. Min Act: -0.1700
Data Index: 7939361 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.1879. Min Act: -0.1700
Data Index: 7332974 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.4066. Min Act: -0.1700
Data Index: 5790678 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6566. Min Range: -6.6566
Max Act: 6.1566. Min Act: -0.1700
Data Index: 3908642 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19