Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4194 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0468. Min Range: -8.0468
Max Act: 8.0468. Min Act: -0.1700
Data Index: 4037563 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0468. Min Range: -8.0468
Max Act: 7.9843. Min Act: -0.1700
Data Index: 2987142 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0468. Min Range: -8.0468
Max Act: 7.9531. Min Act: -0.1700
Data Index: 5882971 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0468. Min Range: -8.0468
Max Act: 7.7343. Min Act: -0.1700
Data Index: 5646327 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0468. Min Range: -8.0468
Max Act: 7.7031. Min Act: -0.1700
Data Index: 2061621 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0468. Min Range: -8.0468
Max Act: 7.6093. Min Act: -0.1700
Data Index: 6340843 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0468. Min Range: -8.0468
Max Act: 7.5781. Min Act: -0.1700
Data Index: 5135532 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0468. Min Range: -8.0468
Max Act: 7.5156. Min Act: -0.1700
Data Index: 6993998 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0468. Min Range: -8.0468
Max Act: 7.4843. Min Act: -0.1700
Data Index: 6892192 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0468. Min Range: -8.0468
Max Act: 7.5156. Min Act: -0.1700
Data Index: 571874 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0468. Min Range: -8.0468
Max Act: 7.5156. Min Act: -0.1700
Data Index: 6315590 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0468. Min Range: -8.0468
Max Act: 7.4843. Min Act: -0.1700
Data Index: 1358489 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0468. Min Range: -8.0468
Max Act: 7.4531. Min Act: -0.1700
Data Index: 582397 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0468. Min Range: -8.0468
Max Act: 7.4531. Min Act: -0.1700
Data Index: 2997599 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0468. Min Range: -8.0468
Max Act: 7.4218. Min Act: -0.1700
Data Index: 8722938 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0468. Min Range: -8.0468
Max Act: 7.4218. Min Act: -0.1700
Data Index: 62774 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0468. Min Range: -8.0468
Max Act: 7.4218. Min Act: -0.1700
Data Index: 6114975 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0468. Min Range: -8.0468
Max Act: 7.4218. Min Act: -0.1700
Data Index: 7958760 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0468. Min Range: -8.0468
Max Act: 7.4218. Min Act: -0.1700
Data Index: 46372 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0468. Min Range: -8.0468
Max Act: 7.4218. Min Act: -0.1700
Data Index: 6938299 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19