Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3396 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0768. Min Range: -7.0768
Max Act: 7.0768. Min Act: -0.1700
Data Index: 712985 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0768. Min Range: -7.0768
Max Act: 7.0456. Min Act: -0.1700
Data Index: 5644037 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0768. Min Range: -7.0768
Max Act: 6.8268. Min Act: -0.1700
Data Index: 4627606 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0768. Min Range: -7.0768
Max Act: 6.6706. Min Act: -0.1700
Data Index: 6231853 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0768. Min Range: -7.0768
Max Act: 6.6393. Min Act: -0.1700
Data Index: 1830552 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0768. Min Range: -7.0768
Max Act: 6.6393. Min Act: -0.1700
Data Index: 7319681 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0768. Min Range: -7.0768
Max Act: 6.6393. Min Act: -0.1700
Data Index: 7001225 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0768. Min Range: -7.0768
Max Act: 6.6393. Min Act: -0.1700
Data Index: 4423839 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0768. Min Range: -7.0768
Max Act: 6.5768. Min Act: -0.1700
Data Index: 6187615 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0768. Min Range: -7.0768
Max Act: 6.5456. Min Act: -0.1700
Data Index: 7961563 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0768. Min Range: -7.0768
Max Act: 6.5456. Min Act: -0.1700
Data Index: 8573419 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0768. Min Range: -7.0768
Max Act: 6.5143. Min Act: -0.1700
Data Index: 8518834 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0768. Min Range: -7.0768
Max Act: 6.5143. Min Act: -0.1700
Data Index: 6317908 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0768. Min Range: -7.0768
Max Act: 6.5143. Min Act: -0.1700
Data Index: 285810 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0768. Min Range: -7.0768
Max Act: 6.5143. Min Act: -0.1700
Data Index: 847723 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0768. Min Range: -7.0768
Max Act: 6.4831. Min Act: -0.1700
Data Index: 2863741 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0768. Min Range: -7.0768
Max Act: 6.5143. Min Act: -0.1700
Data Index: 6459144 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0768. Min Range: -7.0768
Max Act: 6.4831. Min Act: -0.1700
Data Index: 6421968 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0768. Min Range: -7.0768
Max Act: 6.4831. Min Act: -0.1700
Data Index: 1980964 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0768. Min Range: -7.0768
Max Act: 6.4518. Min Act: -0.1700
Data Index: 4071809 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19