Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2479 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.8918. Min Act: -0.1700
Data Index: 6199810 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.7980. Min Act: -0.1700
Data Index: 4574922 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.7980. Min Act: -0.1700
Data Index: 3841511 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.7980. Min Act: -0.1700
Data Index: 997018 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.7668. Min Act: -0.1700
Data Index: 7232109 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.7355. Min Act: -0.1700
Data Index: 8558098 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.6730. Min Act: -0.1700
Data Index: 8683653 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.7043. Min Act: -0.1700
Data Index: 1217007 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.6730. Min Act: -0.1700
Data Index: 5206762 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.6730. Min Act: -0.1700
Data Index: 123916 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.6730. Min Act: -0.1700
Data Index: 6289820 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.6730. Min Act: -0.1700
Data Index: 3774762 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.6418. Min Act: -0.1700
Data Index: 4303690 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.6105. Min Act: -0.1700
Data Index: 2768796 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.6105. Min Act: -0.1700
Data Index: 99435 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.6105. Min Act: -0.1700
Data Index: 2810030 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.6105. Min Act: -0.1700
Data Index: 8633914 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.5793. Min Act: -0.1700
Data Index: 3212895 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.5793. Min Act: -0.1700
Data Index: 3195864 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8918. Min Range: -4.8918
Max Act: 4.5793. Min Act: -0.1700
Data Index: 1994372 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19