Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1466 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1219. Min Range: -6.1219
Max Act: 6.1219. Min Act: -0.1700
Data Index: 7283530 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1219. Min Range: -6.1219
Max Act: 5.9969. Min Act: -0.1700
Data Index: 6309318 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1219. Min Range: -6.1219
Max Act: 5.9657. Min Act: -0.1700
Data Index: 432596 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1219. Min Range: -6.1219
Max Act: 5.8719. Min Act: -0.1699
Data Index: 5221932 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1219. Min Range: -6.1219
Max Act: 5.9032. Min Act: -0.1700
Data Index: 8149185 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1219. Min Range: -6.1219
Max Act: 5.9032. Min Act: -0.1700
Data Index: 6516139 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1219. Min Range: -6.1219
Max Act: 5.9032. Min Act: -0.1700
Data Index: 969852 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1219. Min Range: -6.1219
Max Act: 5.9032. Min Act: -0.1700
Data Index: 47576 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1219. Min Range: -6.1219
Max Act: 5.8407. Min Act: -0.1700
Data Index: 5050255 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1219. Min Range: -6.1219
Max Act: 5.8407. Min Act: -0.1700
Data Index: 4087965 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1219. Min Range: -6.1219
Max Act: 5.8094. Min Act: -0.1699
Data Index: 7478863 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1219. Min Range: -6.1219
Max Act: 5.8094. Min Act: -0.1700
Data Index: 8127409 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1219. Min Range: -6.1219
Max Act: 5.8094. Min Act: -0.1700
Data Index: 1774565 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1219. Min Range: -6.1219
Max Act: 5.8094. Min Act: -0.1699
Data Index: 6666615 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1219. Min Range: -6.1219
Max Act: 5.7782. Min Act: -0.1700
Data Index: 8741961 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1219. Min Range: -6.1219
Max Act: 5.7469. Min Act: -0.1700
Data Index: 4117849 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1219. Min Range: -6.1219
Max Act: 5.7782. Min Act: -0.1694
Data Index: 6833614 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1219. Min Range: -6.1219
Max Act: 5.7782. Min Act: -0.1700
Data Index: 3298059 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1219. Min Range: -6.1219
Max Act: 5.7782. Min Act: -0.1700
Data Index: 7689539 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1219. Min Range: -6.1219
Max Act: 5.7782. Min Act: -0.1700
Data Index: 4431733 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19