Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 972 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.8494. Min Act: -0.1700
Data Index: 8523239 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.5994. Min Act: -0.1700
Data Index: 2084689 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.5369. Min Act: -0.1700
Data Index: 4909941 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.5369. Min Act: -0.1700
Data Index: 3778574 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.5369. Min Act: -0.1700
Data Index: 1637178 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.5369. Min Act: -0.1700
Data Index: 5134599 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.4744. Min Act: -0.1700
Data Index: 3581881 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.4744. Min Act: -0.1700
Data Index: 4327226 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.4119. Min Act: -0.1700
Data Index: 1099230 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.4119. Min Act: -0.1700
Data Index: 681512 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.3494. Min Act: -0.1700
Data Index: 2754978 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.3494. Min Act: -0.1700
Data Index: 2605558 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.3494. Min Act: -0.1700
Data Index: 944912 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.3494. Min Act: -0.1700
Data Index: 7196157 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.2869. Min Act: -0.1700
Data Index: 3890028 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.2869. Min Act: -0.1700
Data Index: 701038 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.2244. Min Act: -0.1700
Data Index: 3994935 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.2869. Min Act: -0.1700
Data Index: 1099727 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.0994. Min Act: -0.1700
Data Index: 2845279 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8494. Min Range: -8.8494
Max Act: 8.2869. Min Act: -0.1700
Data Index: 563425 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19