Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1079 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1850. Min Range: -9.1850
Max Act: 9.1850. Min Act: -0.1700
Data Index: 1739140 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1850. Min Range: -9.1850
Max Act: 8.6850. Min Act: -0.1700
Data Index: 959391 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1850. Min Range: -9.1850
Max Act: 8.6850. Min Act: -0.1700
Data Index: 6120543 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1850. Min Range: -9.1850
Max Act: 8.6225. Min Act: -0.1700
Data Index: 6889232 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1850. Min Range: -9.1850
Max Act: 8.6225. Min Act: -0.1700
Data Index: 893014 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1850. Min Range: -9.1850
Max Act: 8.6225. Min Act: -0.1700
Data Index: 7932335 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1850. Min Range: -9.1850
Max Act: 8.4975. Min Act: -0.1700
Data Index: 7987869 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1850. Min Range: -9.1850
Max Act: 8.4975. Min Act: -0.1700
Data Index: 6263227 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1850. Min Range: -9.1850
Max Act: 8.5600. Min Act: -0.1700
Data Index: 6208729 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1850. Min Range: -9.1850
Max Act: 8.4350. Min Act: -0.1700
Data Index: 954712 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1850. Min Range: -9.1850
Max Act: 8.4975. Min Act: -0.1700
Data Index: 1492547 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1850. Min Range: -9.1850
Max Act: 8.3725. Min Act: -0.1700
Data Index: 165645 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1850. Min Range: -9.1850
Max Act: 8.3100. Min Act: -0.1700
Data Index: 4337720 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1850. Min Range: -9.1850
Max Act: 8.3100. Min Act: -0.1700
Data Index: 7526749 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1850. Min Range: -9.1850
Max Act: 8.3100. Min Act: -0.1700
Data Index: 3843984 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1850. Min Range: -9.1850
Max Act: 8.3100. Min Act: -0.1700
Data Index: 3661342 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1850. Min Range: -9.1850
Max Act: 8.3100. Min Act: -0.1700
Data Index: 6133424 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1850. Min Range: -9.1850
Max Act: 8.1850. Min Act: -0.1700
Data Index: 795339 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1850. Min Range: -9.1850
Max Act: 8.2475. Min Act: -0.1700
Data Index: 3128119 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1850. Min Range: -9.1850
Max Act: 8.1850. Min Act: -0.1700
Data Index: 6543275 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19