Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 413 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2128. Min Range: -4.2128
Max Act: 4.2128. Min Act: -0.1700
Data Index: 3951881 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2128. Min Range: -4.2128
Max Act: 4.1815. Min Act: -0.1700
Data Index: 2930962 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2128. Min Range: -4.2128
Max Act: 4.1503. Min Act: -0.1700
Data Index: 2132241 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2128. Min Range: -4.2128
Max Act: 4.1503. Min Act: -0.1700
Data Index: 7443505 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2128. Min Range: -4.2128
Max Act: 4.1503. Min Act: -0.1699
Data Index: 7578360 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2128. Min Range: -4.2128
Max Act: 4.0878. Min Act: -0.1700
Data Index: 7069289 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2128. Min Range: -4.2128
Max Act: 4.0878. Min Act: -0.1685
Data Index: 3195258 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2128. Min Range: -4.2128
Max Act: 4.0565. Min Act: -0.1700
Data Index: 6174988 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2128. Min Range: -4.2128
Max Act: 4.0565. Min Act: -0.1700
Data Index: 642691 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2128. Min Range: -4.2128
Max Act: 4.0252. Min Act: -0.1591
Data Index: 8603488 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2128. Min Range: -4.2128
Max Act: 4.0565. Min Act: -0.1700
Data Index: 512236 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2128. Min Range: -4.2128
Max Act: 4.0565. Min Act: -0.1700
Data Index: 7171118 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2128. Min Range: -4.2128
Max Act: 4.0565. Min Act: -0.1700
Data Index: 804718 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2128. Min Range: -4.2128
Max Act: 4.0252. Min Act: -0.1700
Data Index: 109866 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2128. Min Range: -4.2128
Max Act: 3.9940. Min Act: -0.1697
Data Index: 1524019 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2128. Min Range: -4.2128
Max Act: 4.0252. Min Act: -0.1700
Data Index: 653224 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2128. Min Range: -4.2128
Max Act: 4.0252. Min Act: -0.1700
Data Index: 1532684 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2128. Min Range: -4.2128
Max Act: 4.0252. Min Act: -0.1700
Data Index: 1323266 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2128. Min Range: -4.2128
Max Act: 4.0252. Min Act: -0.1700
Data Index: 4156101 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2128. Min Range: -4.2128
Max Act: 3.9940. Min Act: -0.1700
Data Index: 5725223 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19