Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1705 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1327. Min Act: -0.1700
Data Index: 3337828 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1327. Min Act: -0.1700
Data Index: 3800850 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1639. Min Act: -0.1700
Data Index: 3993187 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1014. Min Act: -0.1700
Data Index: 8473376 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1014. Min Act: -0.1700
Data Index: 7469717 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1014. Min Act: -0.1700
Data Index: 1974981 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1014. Min Act: -0.1700
Data Index: 6940993 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1014. Min Act: -0.1700
Data Index: 6175007 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1014. Min Act: -0.1700
Data Index: 5827982 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1327. Min Act: -0.1700
Data Index: 4028017 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1014. Min Act: -0.1700
Data Index: 1085255 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.0702. Min Act: -0.1700
Data Index: 2145921 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.1014. Min Act: -0.1700
Data Index: 2325479 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.0702. Min Act: -0.1700
Data Index: 7357599 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.0702. Min Act: -0.1700
Data Index: 7500915 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.0702. Min Act: -0.1700
Data Index: 2855063 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.0702. Min Act: -0.1700
Data Index: 8366908 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.0702. Min Act: -0.1700
Data Index: 2867773 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.0702. Min Act: -0.1700
Data Index: 2973435 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1639. Min Range: -4.1639
Max Act: 4.0702. Min Act: -0.1700
Data Index: 2986759 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19