Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 590 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3359. Min Range: -7.3359
Max Act: 7.3359. Min Act: -0.1700
Data Index: 1879088 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3359. Min Range: -7.3359
Max Act: 7.0234. Min Act: -0.1700
Data Index: 6438758 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3359. Min Range: -7.3359
Max Act: 7.0547. Min Act: -0.1700
Data Index: 314155 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3359. Min Range: -7.3359
Max Act: 6.9609. Min Act: -0.1700
Data Index: 1842584 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3359. Min Range: -7.3359
Max Act: 6.9922. Min Act: -0.1700
Data Index: 2487470 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3359. Min Range: -7.3359
Max Act: 6.9297. Min Act: -0.1700
Data Index: 566194 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3359. Min Range: -7.3359
Max Act: 6.9297. Min Act: -0.1700
Data Index: 8022337 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3359. Min Range: -7.3359
Max Act: 6.8359. Min Act: -0.1700
Data Index: 6732993 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3359. Min Range: -7.3359
Max Act: 6.8672. Min Act: -0.1700
Data Index: 3519458 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3359. Min Range: -7.3359
Max Act: 6.8359. Min Act: -0.1700
Data Index: 1202627 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3359. Min Range: -7.3359
Max Act: 6.8047. Min Act: -0.1700
Data Index: 3543631 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3359. Min Range: -7.3359
Max Act: 6.7734. Min Act: -0.1700
Data Index: 7736753 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3359. Min Range: -7.3359
Max Act: 6.7734. Min Act: -0.1700
Data Index: 7869 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3359. Min Range: -7.3359
Max Act: 6.7734. Min Act: -0.1700
Data Index: 5810474 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3359. Min Range: -7.3359
Max Act: 6.7109. Min Act: -0.1700
Data Index: 5100083 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3359. Min Range: -7.3359
Max Act: 6.7109. Min Act: -0.1700
Data Index: 5805280 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3359. Min Range: -7.3359
Max Act: 6.6484. Min Act: -0.1700
Data Index: 4609717 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3359. Min Range: -7.3359
Max Act: 6.6484. Min Act: -0.1700
Data Index: 2178369 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3359. Min Range: -7.3359
Max Act: 6.6172. Min Act: -0.1700
Data Index: 4110806 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3359. Min Range: -7.3359
Max Act: 6.6172. Min Act: -0.1700
Data Index: 4799496 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19