Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2143 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0406. Min Range: -1.0406

Max Act: 1.0406. Min Act: -0.0000

Data Index: 1193509 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.9158. Min Act: -0.0000

Data Index: 644342 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.8287. Min Act: -0.0000

Data Index: 456101 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.8620. Min Act: -0.0000

Data Index: 712 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1024761 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.7740. Min Act: -0.0000

Data Index: 987627 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6892. Min Act: -0.0000

Data Index: 355420 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.7075. Min Act: -0.0000

Data Index: 787932 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.7047. Min Act: -0.0000

Data Index: 408931 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.7444. Min Act: -0.0000

Data Index: 448878 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6682. Min Act: -0.0000

Data Index: 574497 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6953. Min Act: -0.0000

Data Index: 598194 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6651. Min Act: -0.0000

Data Index: 701056 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.5946. Min Act: -0.0000

Data Index: 1009852 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6525. Min Act: -0.0000

Data Index: 35616 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6465. Min Act: -0.0000

Data Index: 963898 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1323531 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6230. Min Act: -0.0000

Data Index: 1314617 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6118. Min Act: -0.0000

Data Index: 885450 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 1.0406. Min Range: -1.0406

Max Act: 0.6138. Min Act: -0.0000

Data Index: 929953 (C4 (Web Text))

Max Activating Token Index: 621