Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3868 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0955. Min Range: -4.0955
Max Act: 4.0955. Min Act: -0.1700
Data Index: 3984225 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0955. Min Range: -4.0955
Max Act: 4.0642. Min Act: -0.1700
Data Index: 4869199 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0955. Min Range: -4.0955
Max Act: 4.0330. Min Act: -0.1700
Data Index: 617719 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0955. Min Range: -4.0955
Max Act: 4.0017. Min Act: -0.1700
Data Index: 459915 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0955. Min Range: -4.0955
Max Act: 4.0017. Min Act: -0.1700
Data Index: 6068716 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0955. Min Range: -4.0955
Max Act: 3.9704. Min Act: -0.1700
Data Index: 905010 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0955. Min Range: -4.0955
Max Act: 3.9704. Min Act: -0.1700
Data Index: 59377 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0955. Min Range: -4.0955
Max Act: 3.9392. Min Act: -0.1700
Data Index: 7309307 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0955. Min Range: -4.0955
Max Act: 3.9392. Min Act: -0.1700
Data Index: 1131330 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0955. Min Range: -4.0955
Max Act: 3.9079. Min Act: -0.1700
Data Index: 320867 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0955. Min Range: -4.0955
Max Act: 3.8766. Min Act: -0.1700
Data Index: 2814787 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0955. Min Range: -4.0955
Max Act: 3.9079. Min Act: -0.1700
Data Index: 4874024 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0955. Min Range: -4.0955
Max Act: 3.8454. Min Act: -0.1700
Data Index: 8163233 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0955. Min Range: -4.0955
Max Act: 3.8141. Min Act: -0.1700
Data Index: 3493424 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0955. Min Range: -4.0955
Max Act: 3.8454. Min Act: -0.1700
Data Index: 8096373 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0955. Min Range: -4.0955
Max Act: 3.8454. Min Act: -0.1700
Data Index: 2186922 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0955. Min Range: -4.0955
Max Act: 3.8141. Min Act: -0.1700
Data Index: 8345657 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0955. Min Range: -4.0955
Max Act: 3.8454. Min Act: -0.1700
Data Index: 3252198 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0955. Min Range: -4.0955
Max Act: 3.8141. Min Act: -0.1700
Data Index: 4004357 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0955. Min Range: -4.0955
Max Act: 3.8141. Min Act: -0.1700
Data Index: 3607876 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19