Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3858 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.1861. Min Act: -0.1700
Data Index: 4614320 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.1861. Min Act: -0.1700
Data Index: 1763195 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.1548. Min Act: -0.1700
Data Index: 2644949 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.1548. Min Act: -0.1700
Data Index: 965584 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.1548. Min Act: -0.1700
Data Index: 621271 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.1236. Min Act: -0.1700
Data Index: 4584447 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.1236. Min Act: -0.1700
Data Index: 2234013 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.0923. Min Act: -0.1700
Data Index: 5463361 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.1236. Min Act: -0.1700
Data Index: 543210 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.1236. Min Act: -0.1700
Data Index: 2187045 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.0923. Min Act: -0.1700
Data Index: 2421612 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.0611. Min Act: -0.1700
Data Index: 666281 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.0611. Min Act: -0.1700
Data Index: 3212929 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.0611. Min Act: -0.1700
Data Index: 749513 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.0611. Min Act: -0.1700
Data Index: 3425668 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.0611. Min Act: -0.1700
Data Index: 1896149 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.0611. Min Act: -0.1700
Data Index: 3500363 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.0611. Min Act: -0.1700
Data Index: 3654811 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.0611. Min Act: -0.1700
Data Index: 1373106 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1861. Min Range: -4.1861
Max Act: 4.0923. Min Act: -0.1700
Data Index: 521772 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19