Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1977 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.4798. Min Act: -0.1700
Data Index: 5494520 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.4485. Min Act: -0.1700
Data Index: 2868886 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.4485. Min Act: -0.1700
Data Index: 1361995 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.4173. Min Act: -0.1700
Data Index: 860686 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.4173. Min Act: -0.1700
Data Index: 7201775 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.4173. Min Act: -0.1700
Data Index: 2185378 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3860. Min Act: -0.1700
Data Index: 7039546 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3860. Min Act: -0.1700
Data Index: 7595810 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3548. Min Act: -0.1700
Data Index: 5298269 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3548. Min Act: -0.1700
Data Index: 894471 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3860. Min Act: -0.1700
Data Index: 2043781 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3548. Min Act: -0.1700
Data Index: 2644701 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3235. Min Act: -0.1700
Data Index: 6422389 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2923. Min Act: -0.1700
Data Index: 6193679 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2923. Min Act: -0.1700
Data Index: 3641396 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3235. Min Act: -0.1700
Data Index: 5286793 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2923. Min Act: -0.1700
Data Index: 6415674 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2610. Min Act: -0.1700
Data Index: 2726048 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2610. Min Act: -0.1700
Data Index: 5416645 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2610. Min Act: -0.1700
Data Index: 2130403 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19