Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3571 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0498. Min Range: -9.0498
Max Act: 9.0498. Min Act: -0.1700
Data Index: 2152058 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0498. Min Range: -9.0498
Max Act: 8.9873. Min Act: -0.1700
Data Index: 6046223 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0498. Min Range: -9.0498
Max Act: 8.9248. Min Act: -0.1700
Data Index: 7863806 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0498. Min Range: -9.0498
Max Act: 8.6748. Min Act: -0.1700
Data Index: 6487116 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0498. Min Range: -9.0498
Max Act: 8.6123. Min Act: -0.1700
Data Index: 5204909 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0498. Min Range: -9.0498
Max Act: 8.6123. Min Act: -0.1700
Data Index: 4651818 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0498. Min Range: -9.0498
Max Act: 8.6123. Min Act: -0.1700
Data Index: 8145905 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0498. Min Range: -9.0498
Max Act: 8.6123. Min Act: -0.1700
Data Index: 652710 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0498. Min Range: -9.0498
Max Act: 8.5498. Min Act: -0.1700
Data Index: 7379403 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0498. Min Range: -9.0498
Max Act: 8.5498. Min Act: -0.1700
Data Index: 5886694 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0498. Min Range: -9.0498
Max Act: 8.4873. Min Act: -0.1700
Data Index: 1171116 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0498. Min Range: -9.0498
Max Act: 8.4873. Min Act: -0.1700
Data Index: 1495656 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0498. Min Range: -9.0498
Max Act: 8.4873. Min Act: -0.1700
Data Index: 2222247 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0498. Min Range: -9.0498
Max Act: 8.4248. Min Act: -0.1700
Data Index: 5663644 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0498. Min Range: -9.0498
Max Act: 8.4248. Min Act: -0.1700
Data Index: 1004036 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0498. Min Range: -9.0498
Max Act: 8.3623. Min Act: -0.1700
Data Index: 7343570 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0498. Min Range: -9.0498
Max Act: 8.3623. Min Act: -0.1700
Data Index: 1394601 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0498. Min Range: -9.0498
Max Act: 8.3623. Min Act: -0.1700
Data Index: 382314 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0498. Min Range: -9.0498
Max Act: 8.3623. Min Act: -0.1700
Data Index: 573256 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0498. Min Range: -9.0498
Max Act: 8.3623. Min Act: -0.1700
Data Index: 6695292 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19