Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5395 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3431. Min Range: -5.3431
Max Act: 5.3431. Min Act: -0.1700
Data Index: 8524150 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3431. Min Range: -5.3431
Max Act: 5.2493. Min Act: -0.1700
Data Index: 619354 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3431. Min Range: -5.3431
Max Act: 5.0618. Min Act: -0.1700
Data Index: 7030663 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3431. Min Range: -5.3431
Max Act: 4.9993. Min Act: -0.1700
Data Index: 6176720 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3431. Min Range: -5.3431
Max Act: 4.9993. Min Act: -0.1700
Data Index: 4042976 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3431. Min Range: -5.3431
Max Act: 4.9681. Min Act: -0.1700
Data Index: 1590224 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3431. Min Range: -5.3431
Max Act: 4.9681. Min Act: -0.1700
Data Index: 8803334 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3431. Min Range: -5.3431
Max Act: 4.9056. Min Act: -0.1700
Data Index: 5380505 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3431. Min Range: -5.3431
Max Act: 4.8743. Min Act: -0.1700
Data Index: 3760901 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3431. Min Range: -5.3431
Max Act: 4.8743. Min Act: -0.1700
Data Index: 4262639 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3431. Min Range: -5.3431
Max Act: 4.8743. Min Act: -0.1700
Data Index: 7645345 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3431. Min Range: -5.3431
Max Act: 4.8431. Min Act: -0.1700
Data Index: 6438974 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3431. Min Range: -5.3431
Max Act: 4.8431. Min Act: -0.1700
Data Index: 6679459 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3431. Min Range: -5.3431
Max Act: 4.8431. Min Act: -0.1700
Data Index: 343585 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3431. Min Range: -5.3431
Max Act: 4.8431. Min Act: -0.1700
Data Index: 8144706 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3431. Min Range: -5.3431
Max Act: 4.8431. Min Act: -0.1700
Data Index: 7870717 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3431. Min Range: -5.3431
Max Act: 4.8118. Min Act: -0.1700
Data Index: 2601531 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3431. Min Range: -5.3431
Max Act: 4.8118. Min Act: -0.1700
Data Index: 658585 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3431. Min Range: -5.3431
Max Act: 4.7805. Min Act: -0.1700
Data Index: 6851468 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3431. Min Range: -5.3431
Max Act: 4.7805. Min Act: -0.1700
Data Index: 2170101 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19