Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1899 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0728. Min Range: -7.0728
Max Act: 7.0728. Min Act: -0.1700
Data Index: 5288172 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0728. Min Range: -7.0728
Max Act: 6.9478. Min Act: -0.1700
Data Index: 7970798 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0728. Min Range: -7.0728
Max Act: 6.9166. Min Act: -0.1700
Data Index: 5751030 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0728. Min Range: -7.0728
Max Act: 6.8541. Min Act: -0.1700
Data Index: 2442694 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0728. Min Range: -7.0728
Max Act: 6.8228. Min Act: -0.1700
Data Index: 6998006 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0728. Min Range: -7.0728
Max Act: 6.7916. Min Act: -0.1700
Data Index: 4125571 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0728. Min Range: -7.0728
Max Act: 6.7916. Min Act: -0.1700
Data Index: 4404823 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0728. Min Range: -7.0728
Max Act: 6.6978. Min Act: -0.1700
Data Index: 2068969 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0728. Min Range: -7.0728
Max Act: 6.6666. Min Act: -0.1700
Data Index: 3497050 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0728. Min Range: -7.0728
Max Act: 6.6353. Min Act: -0.1700
Data Index: 3341302 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0728. Min Range: -7.0728
Max Act: 6.6041. Min Act: -0.1700
Data Index: 8732478 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0728. Min Range: -7.0728
Max Act: 6.5728. Min Act: -0.1700
Data Index: 8301211 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0728. Min Range: -7.0728
Max Act: 6.5728. Min Act: -0.1700
Data Index: 8495358 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0728. Min Range: -7.0728
Max Act: 6.5416. Min Act: -0.1700
Data Index: 7963944 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0728. Min Range: -7.0728
Max Act: 6.5728. Min Act: -0.1700
Data Index: 4353383 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0728. Min Range: -7.0728
Max Act: 6.5416. Min Act: -0.1700
Data Index: 5395995 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0728. Min Range: -7.0728
Max Act: 6.5103. Min Act: -0.1700
Data Index: 8211031 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0728. Min Range: -7.0728
Max Act: 6.5103. Min Act: -0.1700
Data Index: 5690538 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0728. Min Range: -7.0728
Max Act: 6.4791. Min Act: -0.1700
Data Index: 5572288 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0728. Min Range: -7.0728
Max Act: 6.4791. Min Act: -0.1700
Data Index: 1757284 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19