Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 495 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0763. Min Range: -8.0763
Max Act: 8.0763. Min Act: -0.1700
Data Index: 6524313 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0763. Min Range: -8.0763
Max Act: 8.0138. Min Act: -0.1700
Data Index: 4331703 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.7013. Min Act: -0.1700
Data Index: 8013721 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.6701. Min Act: -0.1700
Data Index: 2777294 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.6701. Min Act: -0.1700
Data Index: 6156526 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.5138. Min Act: -0.1700
Data Index: 6800914 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.5763. Min Act: -0.1700
Data Index: 1837704 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.4826. Min Act: -0.1700
Data Index: 3056171 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.4826. Min Act: -0.1700
Data Index: 6231744 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.4513. Min Act: -0.1700
Data Index: 8488945 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.4513. Min Act: -0.1700
Data Index: 109957 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.3576. Min Act: -0.1700
Data Index: 7893923 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.3576. Min Act: -0.1700
Data Index: 332303 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.3576. Min Act: -0.1700
Data Index: 6481066 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.3263. Min Act: -0.1700
Data Index: 1932220 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.2951. Min Act: -0.1700
Data Index: 2395887 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.2951. Min Act: -0.1700
Data Index: 6789268 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.2951. Min Act: -0.1700
Data Index: 5346926 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.2951. Min Act: -0.1700
Data Index: 2395886 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.2951. Min Act: -0.1700
Data Index: 5139779 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19