Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1021 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.6928. Min Act: -0.1700
Data Index: 158331 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.6928. Min Act: -0.1700
Data Index: 1528582 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.6928. Min Act: -0.1700
Data Index: 2902196 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.6303. Min Act: -0.1700
Data Index: 8222374 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.6303. Min Act: -0.1700
Data Index: 7237268 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.4428. Min Act: -0.1700
Data Index: 4945257 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.4116. Min Act: -0.1700
Data Index: 4179425 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.4116. Min Act: -0.1700
Data Index: 7113674 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.3803. Min Act: -0.1700
Data Index: 197701 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.3803. Min Act: -0.1700
Data Index: 6501927 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.2553. Min Act: -0.1700
Data Index: 5760662 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.2866. Min Act: -0.1700
Data Index: 1605924 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.2241. Min Act: -0.1700
Data Index: 2970745 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.2241. Min Act: -0.1700
Data Index: 5279029 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.2241. Min Act: -0.1700
Data Index: 2816900 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.1928. Min Act: -0.1700
Data Index: 693590 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.1616. Min Act: -0.1700
Data Index: 7336100 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.1616. Min Act: -0.1700
Data Index: 3990700 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.1928. Min Act: -0.1700
Data Index: 2427415 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6928. Min Range: -7.6928
Max Act: 7.1303. Min Act: -0.1700
Data Index: 5219134 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19