Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1866 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.9157. Min Act: -0.1700
Data Index: 573616 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.8844. Min Act: -0.1700
Data Index: 3227004 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.8532. Min Act: -0.1700
Data Index: 6524092 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.8219. Min Act: -0.1700
Data Index: 1134000 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.7906. Min Act: -0.1700
Data Index: 236768 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.8219. Min Act: -0.1700
Data Index: 6808903 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.7594. Min Act: -0.1700
Data Index: 2789304 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.7594. Min Act: -0.1700
Data Index: 1320946 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.7906. Min Act: -0.1700
Data Index: 4602786 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.7594. Min Act: -0.1700
Data Index: 6351612 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.7594. Min Act: -0.1700
Data Index: 3206522 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.7281. Min Act: -0.1700
Data Index: 113576 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.7281. Min Act: -0.1700
Data Index: 837180 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.6655. Min Act: -0.1700
Data Index: 8111115 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.7281. Min Act: -0.1700
Data Index: 599332 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.6968. Min Act: -0.1700
Data Index: 8354184 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.6968. Min Act: -0.1700
Data Index: 4749385 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.6968. Min Act: -0.1700
Data Index: 621812 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.6342. Min Act: -0.1700
Data Index: 4458046 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9157. Min Range: -3.9157
Max Act: 3.6655. Min Act: -0.1700
Data Index: 8100596 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19