Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 848 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3265. Min Range: -8.3265
Max Act: 8.3265. Min Act: -0.1700
Data Index: 1984279 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3265. Min Range: -8.3265
Max Act: 8.2640. Min Act: -0.1700
Data Index: 2468290 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3265. Min Range: -8.3265
Max Act: 7.4203. Min Act: -0.1700
Data Index: 6247214 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3265. Min Range: -8.3265
Max Act: 7.2953. Min Act: -0.1700
Data Index: 2468286 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3265. Min Range: -8.3265
Max Act: 7.2015. Min Act: -0.1700
Data Index: 1984274 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3265. Min Range: -8.3265
Max Act: 7.1390. Min Act: -0.1700
Data Index: 4911873 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3265. Min Range: -8.3265
Max Act: 7.0765. Min Act: -0.1700
Data Index: 8178816 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3265. Min Range: -8.3265
Max Act: 7.0765. Min Act: -0.1700
Data Index: 3662523 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3265. Min Range: -8.3265
Max Act: 7.0453. Min Act: -0.1700
Data Index: 1682096 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3265. Min Range: -8.3265
Max Act: 7.0765. Min Act: -0.1700
Data Index: 6334603 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3265. Min Range: -8.3265
Max Act: 7.0140. Min Act: -0.1700
Data Index: 4870437 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3265. Min Range: -8.3265
Max Act: 7.0453. Min Act: -0.1700
Data Index: 5597414 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3265. Min Range: -8.3265
Max Act: 6.9828. Min Act: -0.1700
Data Index: 6000469 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3265. Min Range: -8.3265
Max Act: 6.9828. Min Act: -0.1700
Data Index: 7582827 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3265. Min Range: -8.3265
Max Act: 6.9515. Min Act: -0.1700
Data Index: 4043013 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3265. Min Range: -8.3265
Max Act: 6.9828. Min Act: -0.1700
Data Index: 4758236 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3265. Min Range: -8.3265
Max Act: 6.9515. Min Act: -0.1700
Data Index: 3042398 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3265. Min Range: -8.3265
Max Act: 6.8890. Min Act: -0.1700
Data Index: 5833306 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3265. Min Range: -8.3265
Max Act: 6.8578. Min Act: -0.1700
Data Index: 7227314 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3265. Min Range: -8.3265
Max Act: 6.8578. Min Act: -0.1700
Data Index: 3967439 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19