Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2605 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6120. Min Range: -5.6120
Max Act: 5.6120. Min Act: -0.1700
Data Index: 1189367 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6120. Min Range: -5.6120
Max Act: 5.2057. Min Act: -0.1700
Data Index: 5716716 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6120. Min Range: -5.6120
Max Act: 5.1432. Min Act: -0.1700
Data Index: 1320215 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6120. Min Range: -5.6120
Max Act: 5.1432. Min Act: -0.1700
Data Index: 2666020 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6120. Min Range: -5.6120
Max Act: 4.8620. Min Act: -0.1700
Data Index: 6680749 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6120. Min Range: -5.6120
Max Act: 4.8620. Min Act: -0.1700
Data Index: 2459840 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6120. Min Range: -5.6120
Max Act: 4.8307. Min Act: -0.1700
Data Index: 7864161 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6120. Min Range: -5.6120
Max Act: 4.8620. Min Act: -0.1700
Data Index: 2315605 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6120. Min Range: -5.6120
Max Act: 4.8620. Min Act: -0.1700
Data Index: 7098781 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6120. Min Range: -5.6120
Max Act: 4.8307. Min Act: -0.1700
Data Index: 283788 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6120. Min Range: -5.6120
Max Act: 4.7995. Min Act: -0.1700
Data Index: 4472210 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6120. Min Range: -5.6120
Max Act: 4.7682. Min Act: -0.1700
Data Index: 1019248 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6120. Min Range: -5.6120
Max Act: 4.7995. Min Act: -0.1700
Data Index: 8031992 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6120. Min Range: -5.6120
Max Act: 4.7682. Min Act: -0.1700
Data Index: 691540 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6120. Min Range: -5.6120
Max Act: 4.7682. Min Act: -0.1700
Data Index: 2914039 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6120. Min Range: -5.6120
Max Act: 4.7370. Min Act: -0.1700
Data Index: 494313 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6120. Min Range: -5.6120
Max Act: 4.7370. Min Act: -0.1700
Data Index: 7684300 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6120. Min Range: -5.6120
Max Act: 4.7370. Min Act: -0.1700
Data Index: 3904999 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6120. Min Range: -5.6120
Max Act: 4.7682. Min Act: -0.1700
Data Index: 612384 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6120. Min Range: -5.6120
Max Act: 4.7370. Min Act: -0.1700
Data Index: 3005127 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19