Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1150 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.7252. Min Act: -0.1700
Data Index: 7120435 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.7565. Min Act: -0.1700
Data Index: 902484 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.6940. Min Act: -0.1700
Data Index: 1134167 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.7252. Min Act: -0.1700
Data Index: 6418374 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.6314. Min Act: -0.1700
Data Index: 3655001 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.6157. Min Act: -0.1700
Data Index: 3448232 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.5844. Min Act: -0.1700
Data Index: 6667230 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.5844. Min Act: -0.1700
Data Index: 6367892 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.5844. Min Act: -0.1700
Data Index: 806043 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.5844. Min Act: -0.1700
Data Index: 3655000 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.5531. Min Act: -0.1700
Data Index: 7028726 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.5688. Min Act: -0.1700
Data Index: 1232198 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.5531. Min Act: -0.1700
Data Index: 6815863 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.5061. Min Act: -0.1700
Data Index: 2543754 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.5061. Min Act: -0.1700
Data Index: 3529372 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.4591. Min Act: -0.1700
Data Index: 7718521 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.5218. Min Act: -0.1700
Data Index: 8475075 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.5061. Min Act: -0.1700
Data Index: 8813603 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.4905. Min Act: -0.1700
Data Index: 307137 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7565. Min Range: -3.7565
Max Act: 3.4905. Min Act: -0.1700
Data Index: 76083 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19