Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3508 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2011. Min Range: -4.2011
Max Act: 4.2011. Min Act: -0.1700
Data Index: 2629871 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2011. Min Range: -4.2011
Max Act: 4.1074. Min Act: -0.1700
Data Index: 1762968 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2011. Min Range: -4.2011
Max Act: 4.0761. Min Act: -0.1700
Data Index: 5912324 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2011. Min Range: -4.2011
Max Act: 4.0761. Min Act: -0.1700
Data Index: 7392023 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2011. Min Range: -4.2011
Max Act: 4.0448. Min Act: -0.1700
Data Index: 1112213 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2011. Min Range: -4.2011
Max Act: 4.0448. Min Act: -0.1700
Data Index: 4649791 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2011. Min Range: -4.2011
Max Act: 4.0136. Min Act: -0.1700
Data Index: 3437125 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2011. Min Range: -4.2011
Max Act: 4.0136. Min Act: -0.1700
Data Index: 2581260 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2011. Min Range: -4.2011
Max Act: 4.0136. Min Act: -0.1700
Data Index: 6986986 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.9823. Min Act: -0.1700
Data Index: 8380149 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2011. Min Range: -4.2011
Max Act: 4.0136. Min Act: -0.1700
Data Index: 2149881 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.9823. Min Act: -0.1700
Data Index: 7549435 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.9823. Min Act: -0.1700
Data Index: 6583366 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.9823. Min Act: -0.1700
Data Index: 4975243 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.9511. Min Act: -0.1700
Data Index: 7364378 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.9823. Min Act: -0.1700
Data Index: 496769 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.9198. Min Act: -0.1700
Data Index: 92811 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.9511. Min Act: -0.1700
Data Index: 4431972 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.9511. Min Act: -0.1700
Data Index: 2608957 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2011. Min Range: -4.2011
Max Act: 3.9511. Min Act: -0.1700
Data Index: 4819255 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19