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

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

Neuron 3606 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3143. Min Range: -1.3143

Max Act: 1.3143. Min Act: -0.0002

Data Index: 526215 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 1.3143. Min Range: -1.3143

Max Act: 1.0814. Min Act: -0.0002

Data Index: 128397 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 1.3143. Min Range: -1.3143

Max Act: 1.0412. Min Act: -0.0002

Data Index: 286042 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 1.3143. Min Range: -1.3143

Max Act: 1.0151. Min Act: -0.0001

Data Index: 1252172 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 1.3143. Min Range: -1.3143

Max Act: 1.0013. Min Act: -0.0002

Data Index: 481245 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.9379. Min Act: -0.0001

Data Index: 395393 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.9236. Min Act: -0.0002

Data Index: 388592 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8834. Min Act: -0.0002

Data Index: 829875 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8825. Min Act: -0.0001

Data Index: 479328 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8443. Min Act: -0.0002

Data Index: 386655 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8403. Min Act: -0.0002

Data Index: 373998 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8736. Min Act: -0.0002

Data Index: 639484 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8179. Min Act: -0.0002

Data Index: 207940 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8090. Min Act: -0.0002

Data Index: 701811 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8098. Min Act: -0.0001

Data Index: 845910 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8293. Min Act: -0.0002

Data Index: 1257193 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8118. Min Act: -0.0002

Data Index: 1276736 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.7832. Min Act: -0.0002

Data Index: 572306 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.7820. Min Act: -0.0002

Data Index: 304198 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.7772. Min Act: -0.0002

Data Index: 83354 (C4 (Web Text))

Max Activating Token Index: 488