Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 687 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.2356. Min Act: -0.1700
Data Index: 2905135 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.2670. Min Act: -0.1700
Data Index: 1598643 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.2670. Min Act: -0.1700
Data Index: 1820401 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.2356. Min Act: -0.1700
Data Index: 5980771 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.2356. Min Act: -0.1700
Data Index: 52194 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.2356. Min Act: -0.1700
Data Index: 6512321 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.2356. Min Act: -0.1700
Data Index: 6550694 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.2356. Min Act: -0.1700
Data Index: 8490290 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.2042. Min Act: -0.1700
Data Index: 5860040 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.2042. Min Act: -0.1700
Data Index: 3831884 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.2042. Min Act: -0.1700
Data Index: 3776380 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.2042. Min Act: -0.1700
Data Index: 8551373 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.2042. Min Act: -0.1700
Data Index: 2490105 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.2042. Min Act: -0.1700
Data Index: 3374989 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.2042. Min Act: -0.1700
Data Index: 7182147 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.2042. Min Act: -0.1700
Data Index: 2940197 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.2042. Min Act: -0.1700
Data Index: 5204577 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.1727. Min Act: -0.1700
Data Index: 127692 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.1727. Min Act: -0.1700
Data Index: 3665901 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2670. Min Range: -3.2670
Max Act: 3.1727. Min Act: -0.1700
Data Index: 4527316 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19