Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3185 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.5191. Min Act: -0.1700
Data Index: 842501 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.4566. Min Act: -0.1700
Data Index: 2722210 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.3941. Min Act: -0.1700
Data Index: 2739934 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.3941. Min Act: -0.1700
Data Index: 90047 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.4254. Min Act: -0.1700
Data Index: 842514 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.3629. Min Act: -0.1700
Data Index: 5659190 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.3316. Min Act: -0.1700
Data Index: 1560431 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.3004. Min Act: -0.1700
Data Index: 2739940 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.2691. Min Act: -0.1700
Data Index: 842503 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.3004. Min Act: -0.1700
Data Index: 1851036 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.3004. Min Act: -0.1700
Data Index: 6665276 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.3316. Min Act: -0.1700
Data Index: 2739929 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.2691. Min Act: -0.1700
Data Index: 1560420 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.2691. Min Act: -0.1700
Data Index: 1851034 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.2691. Min Act: -0.1700
Data Index: 2722219 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.2379. Min Act: -0.1700
Data Index: 90051 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.2379. Min Act: -0.1700
Data Index: 2739939 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.1754. Min Act: -0.1700
Data Index: 2739935 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.2066. Min Act: -0.1700
Data Index: 842502 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5191. Min Range: -5.5191
Max Act: 5.2066. Min Act: -0.1700
Data Index: 1534950 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19