Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2114 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7090. Min Range: -8.7090
Max Act: 8.7090. Min Act: -0.1700
Data Index: 7150990 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7090. Min Range: -8.7090
Max Act: 8.6465. Min Act: -0.1700
Data Index: 4730712 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7090. Min Range: -8.7090
Max Act: 8.6465. Min Act: -0.1700
Data Index: 8457771 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7090. Min Range: -8.7090
Max Act: 8.4590. Min Act: -0.1700
Data Index: 7934483 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7090. Min Range: -8.7090
Max Act: 8.3965. Min Act: -0.1700
Data Index: 5946009 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7090. Min Range: -8.7090
Max Act: 8.3340. Min Act: -0.1700
Data Index: 2055343 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7090. Min Range: -8.7090
Max Act: 8.3340. Min Act: -0.1700
Data Index: 4648009 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7090. Min Range: -8.7090
Max Act: 8.3340. Min Act: -0.1700
Data Index: 6955687 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7090. Min Range: -8.7090
Max Act: 8.2715. Min Act: -0.1700
Data Index: 8548267 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7090. Min Range: -8.7090
Max Act: 8.2402. Min Act: -0.1700
Data Index: 4382430 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7090. Min Range: -8.7090
Max Act: 8.2090. Min Act: -0.1700
Data Index: 2236320 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7090. Min Range: -8.7090
Max Act: 8.1777. Min Act: -0.1700
Data Index: 3219613 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7090. Min Range: -8.7090
Max Act: 8.1465. Min Act: -0.1700
Data Index: 2374375 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7090. Min Range: -8.7090
Max Act: 8.1152. Min Act: -0.1700
Data Index: 4026362 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7090. Min Range: -8.7090
Max Act: 8.0840. Min Act: -0.1700
Data Index: 6852658 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7090. Min Range: -8.7090
Max Act: 8.0527. Min Act: -0.1700
Data Index: 7920108 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7090. Min Range: -8.7090
Max Act: 8.0527. Min Act: -0.1700
Data Index: 6419943 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7090. Min Range: -8.7090
Max Act: 7.9902. Min Act: -0.1700
Data Index: 7301904 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7090. Min Range: -8.7090
Max Act: 8.0215. Min Act: -0.1700
Data Index: 249562 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7090. Min Range: -8.7090
Max Act: 8.0215. Min Act: -0.1700
Data Index: 5106145 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19