Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4910 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.3887. Min Range: -12.3887
Max Act: 12.3887. Min Act: -0.1700
Data Index: 8163196 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3887. Min Range: -12.3887
Max Act: 12.1387. Min Act: -0.1700
Data Index: 7533036 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3887. Min Range: -12.3887
Max Act: 11.8262. Min Act: -0.1700
Data Index: 6530611 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3887. Min Range: -12.3887
Max Act: 11.7012. Min Act: -0.1700
Data Index: 1884485 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3887. Min Range: -12.3887
Max Act: 11.6387. Min Act: -0.1700
Data Index: 5212207 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3887. Min Range: -12.3887
Max Act: 11.5762. Min Act: -0.1700
Data Index: 4286579 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3887. Min Range: -12.3887
Max Act: 11.5762. Min Act: -0.1700
Data Index: 8618482 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3887. Min Range: -12.3887
Max Act: 11.5762. Min Act: -0.1700
Data Index: 4351612 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3887. Min Range: -12.3887
Max Act: 11.5762. Min Act: -0.1700
Data Index: 6201857 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3887. Min Range: -12.3887
Max Act: 11.5137. Min Act: -0.1700
Data Index: 1745830 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3887. Min Range: -12.3887
Max Act: 11.5137. Min Act: -0.1700
Data Index: 6500585 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3887. Min Range: -12.3887
Max Act: 11.4512. Min Act: -0.1700
Data Index: 2439080 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3887. Min Range: -12.3887
Max Act: 11.3262. Min Act: -0.1700
Data Index: 2876269 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3887. Min Range: -12.3887
Max Act: 11.3262. Min Act: -0.1700
Data Index: 6994111 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3887. Min Range: -12.3887
Max Act: 11.2637. Min Act: -0.1700
Data Index: 8244162 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3887. Min Range: -12.3887
Max Act: 11.2637. Min Act: -0.1700
Data Index: 3619079 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3887. Min Range: -12.3887
Max Act: 11.2637. Min Act: -0.1700
Data Index: 7582429 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3887. Min Range: -12.3887
Max Act: 11.2637. Min Act: -0.1700
Data Index: 31417 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3887. Min Range: -12.3887
Max Act: 11.2012. Min Act: -0.1700
Data Index: 2810468 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3887. Min Range: -12.3887
Max Act: 11.2012. Min Act: -0.1700
Data Index: 2311487 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19