Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1872 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.7806. Min Act: -0.1700
Data Index: 6207113 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.7493. Min Act: -0.1700
Data Index: 2724612 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.7493. Min Act: -0.1700
Data Index: 8621073 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.7181. Min Act: -0.1700
Data Index: 2722234 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.7181. Min Act: -0.1700
Data Index: 3574104 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.7181. Min Act: -0.1700
Data Index: 2169758 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.6868. Min Act: -0.1700
Data Index: 6894236 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.6868. Min Act: -0.1700
Data Index: 3137137 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.6868. Min Act: -0.1700
Data Index: 3966234 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.7181. Min Act: -0.1700
Data Index: 5385201 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.6868. Min Act: -0.1700
Data Index: 8367005 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.6868. Min Act: -0.1700
Data Index: 3992628 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.6556. Min Act: -0.1699
Data Index: 5068588 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.6243. Min Act: -0.1700
Data Index: 5722944 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.6243. Min Act: -0.1700
Data Index: 5591350 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.6556. Min Act: -0.1700
Data Index: 6813518 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.6556. Min Act: -0.1700
Data Index: 2005230 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.6243. Min Act: -0.1700
Data Index: 6208449 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.5931. Min Act: -0.1700
Data Index: 6487164 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7806. Min Range: -4.7806
Max Act: 4.6243. Min Act: -0.1700
Data Index: 1022585 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19