Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4477 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2282. Min Range: -6.2282
Max Act: 6.2282. Min Act: -0.1700
Data Index: 3437985 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2282. Min Range: -6.2282
Max Act: 6.2282. Min Act: -0.1700
Data Index: 4601608 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2282. Min Range: -6.2282
Max Act: 6.1970. Min Act: -0.1700
Data Index: 3103489 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2282. Min Range: -6.2282
Max Act: 6.1970. Min Act: -0.1700
Data Index: 537642 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2282. Min Range: -6.2282
Max Act: 6.0407. Min Act: -0.1700
Data Index: 7594246 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2282. Min Range: -6.2282
Max Act: 6.0095. Min Act: -0.1700
Data Index: 1787872 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2282. Min Range: -6.2282
Max Act: 5.9782. Min Act: -0.1700
Data Index: 3148134 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2282. Min Range: -6.2282
Max Act: 5.9782. Min Act: -0.1700
Data Index: 1881086 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2282. Min Range: -6.2282
Max Act: 5.9470. Min Act: -0.1700
Data Index: 4504442 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2282. Min Range: -6.2282
Max Act: 5.9470. Min Act: -0.1700
Data Index: 6744364 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2282. Min Range: -6.2282
Max Act: 5.9157. Min Act: -0.1700
Data Index: 2215124 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2282. Min Range: -6.2282
Max Act: 5.8845. Min Act: -0.1700
Data Index: 3729623 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2282. Min Range: -6.2282
Max Act: 5.8845. Min Act: -0.1700
Data Index: 1868351 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2282. Min Range: -6.2282
Max Act: 5.8845. Min Act: -0.1700
Data Index: 2232141 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2282. Min Range: -6.2282
Max Act: 5.8220. Min Act: -0.1700
Data Index: 7280317 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2282. Min Range: -6.2282
Max Act: 5.8532. Min Act: -0.1700
Data Index: 7582153 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2282. Min Range: -6.2282
Max Act: 5.8532. Min Act: -0.1700
Data Index: 2659170 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2282. Min Range: -6.2282
Max Act: 5.8220. Min Act: -0.1700
Data Index: 7356661 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2282. Min Range: -6.2282
Max Act: 5.7907. Min Act: -0.1700
Data Index: 6336197 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2282. Min Range: -6.2282
Max Act: 5.8220. Min Act: -0.1700
Data Index: 5758370 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19