Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4075 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.8005. Min Act: -0.1700
Data Index: 6873746 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.8005. Min Act: -0.1700
Data Index: 5807278 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.8005. Min Act: -0.1700
Data Index: 2830099 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.7367. Min Act: -0.1700
Data Index: 4178930 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.6085. Min Act: -0.1700
Data Index: 932591 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.7047. Min Act: -0.1700
Data Index: 552747 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.6887. Min Act: -0.1700
Data Index: 5122229 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.6887. Min Act: -0.1700
Data Index: 1615103 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.7047. Min Act: -0.1700
Data Index: 1100287 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.7207. Min Act: -0.1700
Data Index: 3774354 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.7207. Min Act: -0.1700
Data Index: 1596833 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.6406. Min Act: -0.1700
Data Index: 474627 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.6727. Min Act: -0.1700
Data Index: 2332875 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.6567. Min Act: -0.1700
Data Index: 4571740 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.6887. Min Act: -0.1700
Data Index: 3141361 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.7846. Min Act: -0.1700
Data Index: 742235 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.7047. Min Act: -0.1700
Data Index: 7581570 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.6887. Min Act: -0.1700
Data Index: 4305614 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.7207. Min Act: -0.1700
Data Index: 2541310 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8005. Min Range: -2.8005
Max Act: 2.6567. Min Act: -0.1700
Data Index: 5641104 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19