Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4043 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.2301. Min Act: -0.1700
Data Index: 2141234 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.1970. Min Act: -0.1700
Data Index: 1650042 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.1637. Min Act: -0.1700
Data Index: 6727042 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.1470. Min Act: -0.1700
Data Index: 132835 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.1470. Min Act: -0.1700
Data Index: 5087892 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.1470. Min Act: -0.1700
Data Index: 4746937 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.1470. Min Act: -0.1700
Data Index: 1674520 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.1304. Min Act: -0.1700
Data Index: 4529404 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.1470. Min Act: -0.1700
Data Index: 902050 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.1470. Min Act: -0.1700
Data Index: 6503717 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.1470. Min Act: -0.1700
Data Index: 3634959 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.0969. Min Act: -0.1700
Data Index: 5502437 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.0969. Min Act: -0.1700
Data Index: 8459584 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.0969. Min Act: -0.1700
Data Index: 6419202 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.0801. Min Act: -0.1700
Data Index: 1498082 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.0801. Min Act: -0.1700
Data Index: 4078955 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.0801. Min Act: -0.1700
Data Index: 1979914 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.0801. Min Act: -0.1700
Data Index: 2718795 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.0969. Min Act: -0.1700
Data Index: 1908768 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2301. Min Range: -2.2301
Max Act: 2.0801. Min Act: -0.1700
Data Index: 8675173 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19