Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4158 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.8551. Min Act: -0.1700
Data Index: 163377 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.8238. Min Act: -0.1700
Data Index: 8688679 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.5113. Min Act: -0.1700
Data Index: 4497016 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.4801. Min Act: -0.1700
Data Index: 1054970 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.4176. Min Act: -0.1700
Data Index: 8178551 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.4176. Min Act: -0.1700
Data Index: 7173686 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.2926. Min Act: -0.1700
Data Index: 4730009 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.2926. Min Act: -0.1700
Data Index: 476149 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.2613. Min Act: -0.1700
Data Index: 7405612 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.2301. Min Act: -0.1700
Data Index: 2577160 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.2613. Min Act: -0.1700
Data Index: 4242202 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.1988. Min Act: -0.1700
Data Index: 935479 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.1988. Min Act: -0.1700
Data Index: 2947477 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.1988. Min Act: -0.1700
Data Index: 6246817 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.1988. Min Act: -0.1700
Data Index: 2550082 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.1676. Min Act: -0.1700
Data Index: 4892863 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.1676. Min Act: -0.1700
Data Index: 4367768 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.1676. Min Act: -0.1700
Data Index: 34396 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.1363. Min Act: -0.1700
Data Index: 359425 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8551. Min Range: -5.8551
Max Act: 5.1363. Min Act: -0.1700
Data Index: 7346906 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19