Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2808 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6009. Min Range: -4.6009
Max Act: 4.6009. Min Act: -0.1700
Data Index: 4997863 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6009. Min Range: -4.6009
Max Act: 4.4134. Min Act: -0.1700
Data Index: 5595238 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6009. Min Range: -4.6009
Max Act: 4.3196. Min Act: -0.1700
Data Index: 4535680 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6009. Min Range: -4.6009
Max Act: 4.3509. Min Act: -0.1700
Data Index: 952447 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6009. Min Range: -4.6009
Max Act: 4.2884. Min Act: -0.1700
Data Index: 7578019 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6009. Min Range: -4.6009
Max Act: 4.2571. Min Act: -0.1700
Data Index: 5974218 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6009. Min Range: -4.6009
Max Act: 4.1946. Min Act: -0.1700
Data Index: 7166439 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6009. Min Range: -4.6009
Max Act: 4.1633. Min Act: -0.1700
Data Index: 287305 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6009. Min Range: -4.6009
Max Act: 4.1633. Min Act: -0.1700
Data Index: 8323180 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6009. Min Range: -4.6009
Max Act: 4.0696. Min Act: -0.1700
Data Index: 3956723 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6009. Min Range: -4.6009
Max Act: 4.0696. Min Act: -0.1700
Data Index: 8352005 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6009. Min Range: -4.6009
Max Act: 4.0383. Min Act: -0.1700
Data Index: 2518996 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6009. Min Range: -4.6009
Max Act: 4.0383. Min Act: -0.1700
Data Index: 7917552 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6009. Min Range: -4.6009
Max Act: 3.9758. Min Act: -0.1700
Data Index: 359764 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6009. Min Range: -4.6009
Max Act: 4.0071. Min Act: -0.1700
Data Index: 4071181 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6009. Min Range: -4.6009
Max Act: 4.0071. Min Act: -0.1700
Data Index: 1158318 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6009. Min Range: -4.6009
Max Act: 3.9758. Min Act: -0.1700
Data Index: 4734151 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6009. Min Range: -4.6009
Max Act: 3.9758. Min Act: -0.1700
Data Index: 7147359 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6009. Min Range: -4.6009
Max Act: 3.9758. Min Act: -0.1700
Data Index: 2187268 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6009. Min Range: -4.6009
Max Act: 3.9445. Min Act: -0.1700
Data Index: 38475 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19