Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4790 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.3097. Min Act: -0.1700
Data Index: 4575154 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.2472. Min Act: -0.1700
Data Index: 564182 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.2159. Min Act: -0.1700
Data Index: 1676350 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.2159. Min Act: -0.1700
Data Index: 7975564 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.1534. Min Act: -0.1700
Data Index: 4105599 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.1222. Min Act: -0.1700
Data Index: 3529489 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.1222. Min Act: -0.1700
Data Index: 8631195 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.1222. Min Act: -0.1700
Data Index: 5989195 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.1222. Min Act: -0.1700
Data Index: 6280066 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.0909. Min Act: -0.1700
Data Index: 1131315 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.0597. Min Act: -0.1700
Data Index: 7015657 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.0597. Min Act: -0.1700
Data Index: 923194 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.0597. Min Act: -0.1700
Data Index: 523419 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.0597. Min Act: -0.1700
Data Index: 1676354 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.0284. Min Act: -0.1700
Data Index: 954751 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.0284. Min Act: -0.1700
Data Index: 2627486 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.0284. Min Act: -0.1700
Data Index: 7490542 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.0597. Min Act: -0.1700
Data Index: 1115068 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.0284. Min Act: -0.1700
Data Index: 3118744 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3097. Min Range: -5.3097
Max Act: 5.0284. Min Act: -0.1700
Data Index: 1839693 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19