Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1483 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.2903. Min Act: -0.1700
Data Index: 6858112 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.1803. Min Act: -0.1700
Data Index: 5968132 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.1488. Min Act: -0.1700
Data Index: 4765770 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.1331. Min Act: -0.1700
Data Index: 2478117 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.1173. Min Act: -0.1700
Data Index: 4492658 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.1173. Min Act: -0.1700
Data Index: 3669602 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.1016. Min Act: -0.1700
Data Index: 2193497 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.1016. Min Act: -0.1700
Data Index: 2352125 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.0858. Min Act: -0.1700
Data Index: 2323727 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.0858. Min Act: -0.1700
Data Index: 7539493 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.0700. Min Act: -0.1700
Data Index: 8692974 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.0700. Min Act: -0.1700
Data Index: 6845851 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.0700. Min Act: -0.1700
Data Index: 2703874 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.0700. Min Act: -0.1700
Data Index: 509586 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.0543. Min Act: -0.1700
Data Index: 2757898 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.0543. Min Act: -0.1700
Data Index: 1491021 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.0700. Min Act: -0.1700
Data Index: 5716876 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.0543. Min Act: -0.1700
Data Index: 6171358 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.0385. Min Act: -0.1700
Data Index: 4626921 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2903. Min Range: -3.2903
Max Act: 3.0385. Min Act: -0.1700
Data Index: 4974737 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19