Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4131 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4750. Min Range: -7.4750
Max Act: 7.4750. Min Act: -0.1700
Data Index: 6151956 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4750. Min Range: -7.4750
Max Act: 7.3500. Min Act: -0.1700
Data Index: 4570874 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4750. Min Range: -7.4750
Max Act: 7.2875. Min Act: -0.1700
Data Index: 6620025 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4750. Min Range: -7.4750
Max Act: 7.2562. Min Act: -0.1700
Data Index: 4495257 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4750. Min Range: -7.4750
Max Act: 7.1937. Min Act: -0.1700
Data Index: 3916410 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4750. Min Range: -7.4750
Max Act: 7.1937. Min Act: -0.1700
Data Index: 40658 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4750. Min Range: -7.4750
Max Act: 7.0687. Min Act: -0.1700
Data Index: 2678674 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4750. Min Range: -7.4750
Max Act: 7.0375. Min Act: -0.1700
Data Index: 8294180 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4750. Min Range: -7.4750
Max Act: 6.9750. Min Act: -0.1700
Data Index: 5769030 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4750. Min Range: -7.4750
Max Act: 6.9750. Min Act: -0.1700
Data Index: 7132000 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4750. Min Range: -7.4750
Max Act: 6.9437. Min Act: -0.1700
Data Index: 1179801 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4750. Min Range: -7.4750
Max Act: 6.9125. Min Act: -0.1700
Data Index: 5930015 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4750. Min Range: -7.4750
Max Act: 6.8500. Min Act: -0.1700
Data Index: 5506173 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4750. Min Range: -7.4750
Max Act: 6.8500. Min Act: -0.1700
Data Index: 3078507 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4750. Min Range: -7.4750
Max Act: 6.8500. Min Act: -0.1700
Data Index: 6933654 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4750. Min Range: -7.4750
Max Act: 6.8187. Min Act: -0.1700
Data Index: 7666119 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4750. Min Range: -7.4750
Max Act: 6.8500. Min Act: -0.1700
Data Index: 5531545 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4750. Min Range: -7.4750
Max Act: 6.8187. Min Act: -0.1700
Data Index: 6993524 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4750. Min Range: -7.4750
Max Act: 6.7875. Min Act: -0.1700
Data Index: 8669530 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4750. Min Range: -7.4750
Max Act: 6.7875. Min Act: -0.1700
Data Index: 6799295 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19