Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2575 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4253. Min Range: -7.4253
Max Act: 7.4253. Min Act: -0.1700
Data Index: 5220394 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4253. Min Range: -7.4253
Max Act: 7.0503. Min Act: -0.1700
Data Index: 3007548 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4253. Min Range: -7.4253
Max Act: 7.0503. Min Act: -0.1700
Data Index: 4774530 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4253. Min Range: -7.4253
Max Act: 6.9566. Min Act: -0.1700
Data Index: 2385278 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4253. Min Range: -7.4253
Max Act: 6.8003. Min Act: -0.1700
Data Index: 5535803 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4253. Min Range: -7.4253
Max Act: 6.7378. Min Act: -0.1700
Data Index: 4844409 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4253. Min Range: -7.4253
Max Act: 6.7378. Min Act: -0.1700
Data Index: 6141590 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4253. Min Range: -7.4253
Max Act: 6.7066. Min Act: -0.1700
Data Index: 860770 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4253. Min Range: -7.4253
Max Act: 6.6753. Min Act: -0.1700
Data Index: 8730438 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4253. Min Range: -7.4253
Max Act: 6.6128. Min Act: -0.1700
Data Index: 7301304 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4253. Min Range: -7.4253
Max Act: 6.6128. Min Act: -0.1700
Data Index: 7465038 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4253. Min Range: -7.4253
Max Act: 6.5816. Min Act: -0.1700
Data Index: 2385280 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4253. Min Range: -7.4253
Max Act: 6.5191. Min Act: -0.1700
Data Index: 5045493 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4253. Min Range: -7.4253
Max Act: 6.4566. Min Act: -0.1700
Data Index: 4856346 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4253. Min Range: -7.4253
Max Act: 6.4253. Min Act: -0.1700
Data Index: 4856349 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4253. Min Range: -7.4253
Max Act: 6.4253. Min Act: -0.1700
Data Index: 5535806 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4253. Min Range: -7.4253
Max Act: 6.3941. Min Act: -0.1700
Data Index: 7009297 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4253. Min Range: -7.4253
Max Act: 6.4253. Min Act: -0.1700
Data Index: 860771 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4253. Min Range: -7.4253
Max Act: 6.4253. Min Act: -0.1700
Data Index: 3007546 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4253. Min Range: -7.4253
Max Act: 6.3941. Min Act: -0.1700
Data Index: 3007550 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19