Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 889 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0560. Min Range: -8.0560
Max Act: 8.0560. Min Act: -0.1700
Data Index: 4264695 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0560. Min Range: -8.0560
Max Act: 7.8685. Min Act: -0.1700
Data Index: 2504121 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0560. Min Range: -8.0560
Max Act: 7.6185. Min Act: -0.1700
Data Index: 243127 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0560. Min Range: -8.0560
Max Act: 7.5872. Min Act: -0.1700
Data Index: 796221 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0560. Min Range: -8.0560
Max Act: 7.5560. Min Act: -0.1700
Data Index: 1063411 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0560. Min Range: -8.0560
Max Act: 7.5560. Min Act: -0.1700
Data Index: 1923516 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0560. Min Range: -8.0560
Max Act: 7.5560. Min Act: -0.1700
Data Index: 1460817 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0560. Min Range: -8.0560
Max Act: 7.5560. Min Act: -0.1700
Data Index: 6141394 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0560. Min Range: -8.0560
Max Act: 7.5247. Min Act: -0.1700
Data Index: 1717916 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0560. Min Range: -8.0560
Max Act: 7.4935. Min Act: -0.1700
Data Index: 7462552 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0560. Min Range: -8.0560
Max Act: 7.4935. Min Act: -0.1700
Data Index: 3863478 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0560. Min Range: -8.0560
Max Act: 7.4310. Min Act: -0.1700
Data Index: 8670658 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0560. Min Range: -8.0560
Max Act: 7.4622. Min Act: -0.1700
Data Index: 2402709 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0560. Min Range: -8.0560
Max Act: 7.4935. Min Act: -0.1700
Data Index: 349874 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0560. Min Range: -8.0560
Max Act: 7.4622. Min Act: -0.1700
Data Index: 5703115 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0560. Min Range: -8.0560
Max Act: 7.4310. Min Act: -0.1700
Data Index: 2342346 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0560. Min Range: -8.0560
Max Act: 7.4310. Min Act: -0.1700
Data Index: 3453468 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0560. Min Range: -8.0560
Max Act: 7.3997. Min Act: -0.1700
Data Index: 5340303 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0560. Min Range: -8.0560
Max Act: 7.3997. Min Act: -0.1700
Data Index: 1270060 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0560. Min Range: -8.0560
Max Act: 7.3997. Min Act: -0.1700
Data Index: 4578746 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19