Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4870 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0328. Min Range: -6.0328
Max Act: 6.0328. Min Act: -0.1700
Data Index: 8624170 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0328. Min Range: -6.0328
Max Act: 5.9390. Min Act: -0.1700
Data Index: 1864657 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0328. Min Range: -6.0328
Max Act: 5.8765. Min Act: -0.1700
Data Index: 5606675 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0328. Min Range: -6.0328
Max Act: 5.8453. Min Act: -0.1700
Data Index: 2783643 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0328. Min Range: -6.0328
Max Act: 5.8453. Min Act: -0.1700
Data Index: 8218699 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0328. Min Range: -6.0328
Max Act: 5.8453. Min Act: -0.1700
Data Index: 2600575 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0328. Min Range: -6.0328
Max Act: 5.8453. Min Act: -0.1700
Data Index: 211851 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0328. Min Range: -6.0328
Max Act: 5.8140. Min Act: -0.1700
Data Index: 8422392 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0328. Min Range: -6.0328
Max Act: 5.8140. Min Act: -0.1700
Data Index: 712061 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0328. Min Range: -6.0328
Max Act: 5.7828. Min Act: -0.1700
Data Index: 3698389 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0328. Min Range: -6.0328
Max Act: 5.7828. Min Act: -0.1700
Data Index: 4824915 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0328. Min Range: -6.0328
Max Act: 5.7828. Min Act: -0.1700
Data Index: 5392186 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0328. Min Range: -6.0328
Max Act: 5.7515. Min Act: -0.1700
Data Index: 604539 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0328. Min Range: -6.0328
Max Act: 5.7515. Min Act: -0.1700
Data Index: 3611804 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0328. Min Range: -6.0328
Max Act: 5.7203. Min Act: -0.1700
Data Index: 4526536 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0328. Min Range: -6.0328
Max Act: 5.7203. Min Act: -0.1700
Data Index: 2401668 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0328. Min Range: -6.0328
Max Act: 5.6890. Min Act: -0.1700
Data Index: 5303265 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0328. Min Range: -6.0328
Max Act: 5.7203. Min Act: -0.1700
Data Index: 7999019 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0328. Min Range: -6.0328
Max Act: 5.7203. Min Act: -0.1700
Data Index: 7461875 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0328. Min Range: -6.0328
Max Act: 5.7203. Min Act: -0.1700
Data Index: 6507102 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19