Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 695 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.9622. Min Act: -0.1700
Data Index: 1644169 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.9622. Min Act: -0.1700
Data Index: 3114779 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.9622. Min Act: -0.1700
Data Index: 5533415 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.8997. Min Act: -0.1700
Data Index: 470807 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.8997. Min Act: -0.1700
Data Index: 8456605 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.7747. Min Act: -0.1700
Data Index: 6206632 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.7747. Min Act: -0.1700
Data Index: 4109118 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.8372. Min Act: -0.1700
Data Index: 4224885 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.7122. Min Act: -0.1700
Data Index: 4548902 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.6497. Min Act: -0.1700
Data Index: 3651709 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.6497. Min Act: -0.1700
Data Index: 3738290 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.6497. Min Act: -0.1700
Data Index: 540542 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.5872. Min Act: -0.1700
Data Index: 5481933 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.5872. Min Act: -0.1700
Data Index: 947258 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.5559. Min Act: -0.1700
Data Index: 1591965 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.5559. Min Act: -0.1700
Data Index: 1703522 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.5247. Min Act: -0.1700
Data Index: 7232274 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.4934. Min Act: -0.1700
Data Index: 5912694 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.4622. Min Act: -0.1700
Data Index: 619405 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.4622. Min Act: -0.1700
Data Index: 1758720 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19