Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5765 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3665. Min Range: -10.3665
Max Act: 10.3665. Min Act: -0.1700
Data Index: 8666738 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3665. Min Range: -10.3665
Max Act: 9.9915. Min Act: -0.1700
Data Index: 5158550 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3665. Min Range: -10.3665
Max Act: 9.9290. Min Act: -0.1700
Data Index: 3502250 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3665. Min Range: -10.3665
Max Act: 9.8665. Min Act: -0.1700
Data Index: 6771288 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3665. Min Range: -10.3665
Max Act: 9.7415. Min Act: -0.1700
Data Index: 1280815 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3665. Min Range: -10.3665
Max Act: 9.7415. Min Act: -0.1700
Data Index: 3865760 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3665. Min Range: -10.3665
Max Act: 9.7415. Min Act: -0.1700
Data Index: 2310248 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3665. Min Range: -10.3665
Max Act: 9.7415. Min Act: -0.1700
Data Index: 6883020 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3665. Min Range: -10.3665
Max Act: 9.6790. Min Act: -0.1700
Data Index: 4329002 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3665. Min Range: -10.3665
Max Act: 9.6790. Min Act: -0.1700
Data Index: 1860502 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3665. Min Range: -10.3665
Max Act: 9.6790. Min Act: -0.1700
Data Index: 2606021 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3665. Min Range: -10.3665
Max Act: 9.6790. Min Act: -0.1700
Data Index: 8598288 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3665. Min Range: -10.3665
Max Act: 9.6790. Min Act: -0.1700
Data Index: 7997383 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3665. Min Range: -10.3665
Max Act: 9.6165. Min Act: -0.1700
Data Index: 2740558 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3665. Min Range: -10.3665
Max Act: 9.5540. Min Act: -0.1700
Data Index: 5265844 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3665. Min Range: -10.3665
Max Act: 9.6165. Min Act: -0.1700
Data Index: 5439467 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3665. Min Range: -10.3665
Max Act: 9.5540. Min Act: -0.1700
Data Index: 4139251 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3665. Min Range: -10.3665
Max Act: 9.5540. Min Act: -0.1700
Data Index: 5786271 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3665. Min Range: -10.3665
Max Act: 9.5540. Min Act: -0.1700
Data Index: 816360 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3665. Min Range: -10.3665
Max Act: 9.5540. Min Act: -0.1700
Data Index: 4750888 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19