Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3414 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9572. Min Range: -9.9572
Max Act: 9.9572. Min Act: -0.1700
Data Index: 1847431 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9572. Min Range: -9.9572
Max Act: 9.7697. Min Act: -0.1700
Data Index: 2538946 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9572. Min Range: -9.9572
Max Act: 9.7072. Min Act: -0.1700
Data Index: 3342821 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9572. Min Range: -9.9572
Max Act: 9.7072. Min Act: -0.1700
Data Index: 3222294 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9572. Min Range: -9.9572
Max Act: 9.5822. Min Act: -0.1700
Data Index: 643200 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9572. Min Range: -9.9572
Max Act: 9.3947. Min Act: -0.1700
Data Index: 863579 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9572. Min Range: -9.9572
Max Act: 9.3322. Min Act: -0.1700
Data Index: 5123786 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9572. Min Range: -9.9572
Max Act: 9.2697. Min Act: -0.1700
Data Index: 6256696 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9572. Min Range: -9.9572
Max Act: 9.2697. Min Act: -0.1700
Data Index: 7603419 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9572. Min Range: -9.9572
Max Act: 9.1447. Min Act: -0.1700
Data Index: 5830556 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9572. Min Range: -9.9572
Max Act: 9.1447. Min Act: -0.1700
Data Index: 8144150 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9572. Min Range: -9.9572
Max Act: 9.1447. Min Act: -0.1700
Data Index: 7122720 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9572. Min Range: -9.9572
Max Act: 9.1447. Min Act: -0.1700
Data Index: 1293352 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9572. Min Range: -9.9572
Max Act: 9.0822. Min Act: -0.1700
Data Index: 2746510 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9572. Min Range: -9.9572
Max Act: 9.0822. Min Act: -0.1700
Data Index: 4854552 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9572. Min Range: -9.9572
Max Act: 9.0822. Min Act: -0.1700
Data Index: 4903819 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9572. Min Range: -9.9572
Max Act: 8.9572. Min Act: -0.1700
Data Index: 5870241 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9572. Min Range: -9.9572
Max Act: 9.0197. Min Act: -0.1700
Data Index: 6536003 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9572. Min Range: -9.9572
Max Act: 9.0197. Min Act: -0.1700
Data Index: 4598589 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9572. Min Range: -9.9572
Max Act: 9.0197. Min Act: -0.1700
Data Index: 662870 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19