Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1868 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3052. Min Range: -5.3052
Max Act: 5.2740. Min Act: -0.1700
Data Index: 7407426 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3052. Min Range: -5.3052
Max Act: 5.3052. Min Act: -0.1700
Data Index: 4254533 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3052. Min Range: -5.3052
Max Act: 5.1802. Min Act: -0.1700
Data Index: 508373 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3052. Min Range: -5.3052
Max Act: 5.1490. Min Act: -0.1700
Data Index: 1605908 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3052. Min Range: -5.3052
Max Act: 5.0865. Min Act: -0.1700
Data Index: 4825600 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3052. Min Range: -5.3052
Max Act: 5.0865. Min Act: -0.1700
Data Index: 2646305 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3052. Min Range: -5.3052
Max Act: 5.0552. Min Act: -0.1700
Data Index: 6984617 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3052. Min Range: -5.3052
Max Act: 5.0865. Min Act: -0.1700
Data Index: 8653114 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3052. Min Range: -5.3052
Max Act: 5.0552. Min Act: -0.1700
Data Index: 3421765 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3052. Min Range: -5.3052
Max Act: 5.0240. Min Act: -0.1700
Data Index: 5670573 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3052. Min Range: -5.3052
Max Act: 5.0240. Min Act: -0.1700
Data Index: 65869 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3052. Min Range: -5.3052
Max Act: 5.0240. Min Act: -0.1700
Data Index: 5048307 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3052. Min Range: -5.3052
Max Act: 5.0865. Min Act: -0.1700
Data Index: 1321452 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3052. Min Range: -5.3052
Max Act: 5.0240. Min Act: -0.1700
Data Index: 985704 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3052. Min Range: -5.3052
Max Act: 5.0240. Min Act: -0.1700
Data Index: 311768 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3052. Min Range: -5.3052
Max Act: 5.0240. Min Act: -0.1700
Data Index: 3008299 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3052. Min Range: -5.3052
Max Act: 5.0240. Min Act: -0.1700
Data Index: 7609202 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3052. Min Range: -5.3052
Max Act: 4.9927. Min Act: -0.1700
Data Index: 4986425 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3052. Min Range: -5.3052
Max Act: 4.9302. Min Act: -0.1700
Data Index: 6053708 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3052. Min Range: -5.3052
Max Act: 4.9615. Min Act: -0.1700
Data Index: 2061191 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19