Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5023 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.9708. Min Range: -11.9708
Max Act: 11.9708. Min Act: -0.1700
Data Index: 8729815 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9708. Min Range: -11.9708
Max Act: 11.6583. Min Act: -0.1700
Data Index: 7225006 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9708. Min Range: -11.9708
Max Act: 11.5958. Min Act: -0.1700
Data Index: 207629 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9708. Min Range: -11.9708
Max Act: 11.5333. Min Act: -0.1700
Data Index: 4492203 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9708. Min Range: -11.9708
Max Act: 11.2833. Min Act: -0.1700
Data Index: 2679716 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9708. Min Range: -11.9708
Max Act: 11.2208. Min Act: -0.1700
Data Index: 7957126 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9708. Min Range: -11.9708
Max Act: 11.2208. Min Act: -0.1700
Data Index: 2924146 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9708. Min Range: -11.9708
Max Act: 11.1583. Min Act: -0.1700
Data Index: 3893066 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9708. Min Range: -11.9708
Max Act: 11.0958. Min Act: -0.1700
Data Index: 5272832 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9708. Min Range: -11.9708
Max Act: 11.1583. Min Act: -0.1700
Data Index: 3577629 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9708. Min Range: -11.9708
Max Act: 11.0333. Min Act: -0.1700
Data Index: 3575705 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9708. Min Range: -11.9708
Max Act: 11.0333. Min Act: -0.1700
Data Index: 1710763 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9708. Min Range: -11.9708
Max Act: 10.9083. Min Act: -0.1700
Data Index: 6309662 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9708. Min Range: -11.9708
Max Act: 10.9708. Min Act: -0.1700
Data Index: 4469832 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9708. Min Range: -11.9708
Max Act: 10.9708. Min Act: -0.1700
Data Index: 2908827 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9708. Min Range: -11.9708
Max Act: 10.9708. Min Act: -0.1700
Data Index: 4761804 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9708. Min Range: -11.9708
Max Act: 10.9083. Min Act: -0.1700
Data Index: 8174219 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9708. Min Range: -11.9708
Max Act: 10.9708. Min Act: -0.1700
Data Index: 4688832 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9708. Min Range: -11.9708
Max Act: 10.7833. Min Act: -0.1700
Data Index: 7124734 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9708. Min Range: -11.9708
Max Act: 10.7833. Min Act: -0.1700
Data Index: 5817824 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19