Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3243 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1879. Min Range: -5.1879
Max Act: 5.1879. Min Act: -0.1700
Data Index: 1461431 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1879. Min Range: -5.1879
Max Act: 5.1567. Min Act: -0.1700
Data Index: 1080283 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1879. Min Range: -5.1879
Max Act: 5.0004. Min Act: -0.1700
Data Index: 2923367 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1879. Min Range: -5.1879
Max Act: 5.0004. Min Act: -0.1700
Data Index: 3868400 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1879. Min Range: -5.1879
Max Act: 4.9692. Min Act: -0.1700
Data Index: 8574472 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1879. Min Range: -5.1879
Max Act: 4.9692. Min Act: -0.1700
Data Index: 58520 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1879. Min Range: -5.1879
Max Act: 4.9692. Min Act: -0.1700
Data Index: 932474 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1879. Min Range: -5.1879
Max Act: 4.9379. Min Act: -0.1700
Data Index: 2437592 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1879. Min Range: -5.1879
Max Act: 4.8754. Min Act: -0.1700
Data Index: 1406665 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1879. Min Range: -5.1879
Max Act: 4.8754. Min Act: -0.1700
Data Index: 1697325 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1879. Min Range: -5.1879
Max Act: 4.8754. Min Act: -0.1700
Data Index: 4895824 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1879. Min Range: -5.1879
Max Act: 4.8754. Min Act: -0.1700
Data Index: 117681 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1879. Min Range: -5.1879
Max Act: 4.8442. Min Act: -0.1700
Data Index: 4205814 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1879. Min Range: -5.1879
Max Act: 4.8129. Min Act: -0.1700
Data Index: 6886733 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1879. Min Range: -5.1879
Max Act: 4.8129. Min Act: -0.1700
Data Index: 3526339 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1879. Min Range: -5.1879
Max Act: 4.8129. Min Act: -0.1700
Data Index: 2907714 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1879. Min Range: -5.1879
Max Act: 4.8129. Min Act: -0.1700
Data Index: 8424424 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1879. Min Range: -5.1879
Max Act: 4.7817. Min Act: -0.1700
Data Index: 977926 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1879. Min Range: -5.1879
Max Act: 4.7504. Min Act: -0.1700
Data Index: 5079842 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1879. Min Range: -5.1879
Max Act: 4.7817. Min Act: -0.1700
Data Index: 1404718 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19