Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1396. Min Range: -6.1396
Max Act: 6.1396. Min Act: -0.1700
Data Index: 8143671 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1396. Min Range: -6.1396
Max Act: 6.0771. Min Act: -0.1700
Data Index: 2388491 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1396. Min Range: -6.1396
Max Act: 6.0771. Min Act: -0.1700
Data Index: 8143680 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1396. Min Range: -6.1396
Max Act: 6.0771. Min Act: -0.1700
Data Index: 4987162 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1396. Min Range: -6.1396
Max Act: 6.0146. Min Act: -0.1700
Data Index: 6791709 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1396. Min Range: -6.1396
Max Act: 5.9833. Min Act: -0.1700
Data Index: 8143682 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1396. Min Range: -6.1396
Max Act: 5.9521. Min Act: -0.1700
Data Index: 6401673 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1396. Min Range: -6.1396
Max Act: 5.9208. Min Act: -0.1700
Data Index: 370504 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1396. Min Range: -6.1396
Max Act: 5.8896. Min Act: -0.1700
Data Index: 3256341 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1396. Min Range: -6.1396
Max Act: 5.8896. Min Act: -0.1700
Data Index: 3020755 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1396. Min Range: -6.1396
Max Act: 5.8583. Min Act: -0.1700
Data Index: 4648986 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1396. Min Range: -6.1396
Max Act: 5.8583. Min Act: -0.1700
Data Index: 4169665 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1396. Min Range: -6.1396
Max Act: 5.8583. Min Act: -0.1700
Data Index: 6690096 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1396. Min Range: -6.1396
Max Act: 5.8583. Min Act: -0.1700
Data Index: 1221898 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1396. Min Range: -6.1396
Max Act: 5.8271. Min Act: -0.1700
Data Index: 4992609 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1396. Min Range: -6.1396
Max Act: 5.7958. Min Act: -0.1700
Data Index: 7569288 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1396. Min Range: -6.1396
Max Act: 5.7958. Min Act: -0.1700
Data Index: 7595952 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1396. Min Range: -6.1396
Max Act: 5.7646. Min Act: -0.1700
Data Index: 3276951 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1396. Min Range: -6.1396
Max Act: 5.7646. Min Act: -0.1700
Data Index: 4500903 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1396. Min Range: -6.1396
Max Act: 5.7333. Min Act: -0.1700
Data Index: 3321117 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19