Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4036 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.7590. Min Act: -0.1700
Data Index: 982026 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.7158. Min Act: -0.1700
Data Index: 8190276 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.6985. Min Act: -0.1700
Data Index: 7047812 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.6985. Min Act: -0.1700
Data Index: 5405613 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.6985. Min Act: -0.1700
Data Index: 4563480 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.6985. Min Act: -0.1700
Data Index: 4887037 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.6898. Min Act: -0.1700
Data Index: 1358177 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.6898. Min Act: -0.1700
Data Index: 5024071 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.6898. Min Act: -0.1700
Data Index: 6148900 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.6898. Min Act: -0.1700
Data Index: 7079030 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.6811. Min Act: -0.1700
Data Index: 4750590 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.6724. Min Act: -0.1700
Data Index: 1401403 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.6724. Min Act: -0.1700
Data Index: 3812350 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.6724. Min Act: -0.1700
Data Index: 2028466 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.6811. Min Act: -0.1700
Data Index: 8130226 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.6811. Min Act: -0.1700
Data Index: 1292297 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.6811. Min Act: -0.1700
Data Index: 4775425 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.6637. Min Act: -0.1700
Data Index: 7885735 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.6637. Min Act: -0.1700
Data Index: 7397715 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7590. Min Range: -1.7590
Max Act: 1.6724. Min Act: -0.1700
Data Index: 2745512 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19