Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3066 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.5773. Min Act: -0.1700
Data Index: 8782559 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.5148. Min Act: -0.1700
Data Index: 2184486 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.3898. Min Act: -0.1700
Data Index: 3600386 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.4210. Min Act: -0.1700
Data Index: 1248226 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.4210. Min Act: -0.1700
Data Index: 4449955 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.3898. Min Act: -0.1700
Data Index: 5340949 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.3585. Min Act: -0.1700
Data Index: 8775352 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.3585. Min Act: -0.1700
Data Index: 1528799 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.3273. Min Act: -0.1700
Data Index: 1222732 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.2960. Min Act: -0.1700
Data Index: 7919482 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.2960. Min Act: -0.1700
Data Index: 8363986 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.2960. Min Act: -0.1700
Data Index: 1094960 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.2648. Min Act: -0.1700
Data Index: 4633339 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.2648. Min Act: -0.1700
Data Index: 2066795 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.2960. Min Act: -0.1700
Data Index: 4883023 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.2335. Min Act: -0.1700
Data Index: 1021976 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.2023. Min Act: -0.1700
Data Index: 1579202 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.1398. Min Act: -0.1700
Data Index: 1866592 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.1398. Min Act: -0.1700
Data Index: 8190822 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5773. Min Range: -7.5773
Max Act: 7.1710. Min Act: -0.1700
Data Index: 7851205 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19