Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 153 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3320. Min Range: -5.3320
Max Act: 5.3320. Min Act: -0.1700
Data Index: 3874274 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3320. Min Range: -5.3320
Max Act: 5.3320. Min Act: -0.1700
Data Index: 1097359 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3320. Min Range: -5.3320
Max Act: 5.3320. Min Act: -0.1700
Data Index: 5152697 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3320. Min Range: -5.3320
Max Act: 5.2382. Min Act: -0.1700
Data Index: 6380635 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3320. Min Range: -5.3320
Max Act: 5.1757. Min Act: -0.1700
Data Index: 3984312 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3320. Min Range: -5.3320
Max Act: 5.1445. Min Act: -0.1700
Data Index: 4239500 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3320. Min Range: -5.3320
Max Act: 5.1445. Min Act: -0.1700
Data Index: 3581273 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3320. Min Range: -5.3320
Max Act: 5.0820. Min Act: -0.1700
Data Index: 2389729 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3320. Min Range: -5.3320
Max Act: 5.0820. Min Act: -0.1700
Data Index: 2735479 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3320. Min Range: -5.3320
Max Act: 5.0820. Min Act: -0.1700
Data Index: 3984298 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3320. Min Range: -5.3320
Max Act: 5.0507. Min Act: -0.1700
Data Index: 4765391 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3320. Min Range: -5.3320
Max Act: 5.0507. Min Act: -0.1700
Data Index: 3984314 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3320. Min Range: -5.3320
Max Act: 5.0507. Min Act: -0.1700
Data Index: 4930540 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3320. Min Range: -5.3320
Max Act: 5.0507. Min Act: -0.1700
Data Index: 2077836 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3320. Min Range: -5.3320
Max Act: 5.0195. Min Act: -0.1700
Data Index: 3984324 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3320. Min Range: -5.3320
Max Act: 5.0195. Min Act: -0.1700
Data Index: 3984318 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3320. Min Range: -5.3320
Max Act: 5.0195. Min Act: -0.1700
Data Index: 4193969 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3320. Min Range: -5.3320
Max Act: 5.0195. Min Act: -0.1700
Data Index: 3658197 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3320. Min Range: -5.3320
Max Act: 4.9882. Min Act: -0.1700
Data Index: 3984320 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3320. Min Range: -5.3320
Max Act: 4.9882. Min Act: -0.1700
Data Index: 3984322 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19