Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5752 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.8898. Min Act: -0.1700
Data Index: 3359689 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.6398. Min Act: -0.1700
Data Index: 6703974 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.4523. Min Act: -0.1700
Data Index: 4824064 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.3898. Min Act: -0.1700
Data Index: 2860378 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.3898. Min Act: -0.1700
Data Index: 5662278 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.3898. Min Act: -0.1700
Data Index: 6786620 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.3273. Min Act: -0.1700
Data Index: 720240 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.2648. Min Act: -0.1700
Data Index: 8511321 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.2648. Min Act: -0.1700
Data Index: 8584198 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.2648. Min Act: -0.1700
Data Index: 7331588 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.2023. Min Act: -0.1700
Data Index: 4150691 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.2648. Min Act: -0.1700
Data Index: 771440 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.2023. Min Act: -0.1700
Data Index: 4059066 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.2023. Min Act: -0.1700
Data Index: 1224440 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.2023. Min Act: -0.1700
Data Index: 8520392 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.1398. Min Act: -0.1700
Data Index: 4359335 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.0773. Min Act: -0.1700
Data Index: 6441280 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.1398. Min Act: -0.1700
Data Index: 6301800 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.1398. Min Act: -0.1700
Data Index: 5138339 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8898. Min Range: -8.8898
Max Act: 8.1398. Min Act: -0.1700
Data Index: 2181898 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19