Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 806 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1936. Min Range: -1.1936

Max Act: 1.1936. Min Act: -0.0000

Data Index: 783222 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.9085. Min Act: -0.0001

Data Index: 928696 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.9139. Min Act: -0.0000

Data Index: 236678 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.9116. Min Act: -0.0000

Data Index: 1050127 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1265416 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.8968. Min Act: -0.0001

Data Index: 280818 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.8729. Min Act: -0.0000

Data Index: 670406 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.8996. Min Act: -0.0000

Data Index: 359791 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1075284 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.8910. Min Act: -0.0001

Data Index: 631693 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.8654. Min Act: -0.0000

Data Index: 1228003 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.8878. Min Act: -0.0001

Data Index: 768102 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.8617. Min Act: -0.0000

Data Index: 109455 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.8986. Min Act: -0.0000

Data Index: 730313 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.8118. Min Act: -0.0001

Data Index: 989808 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.8154. Min Act: -0.0000

Data Index: 439795 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.8359. Min Act: -0.0000

Data Index: 107937 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.7982. Min Act: -0.0000

Data Index: 832363 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.7940. Min Act: -0.0000

Data Index: 758253 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.7894. Min Act: -0.0001

Data Index: 345853 (C4 (Web Text))

Max Activating Token Index: 276