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

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

Neuron 84 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: 1.7421. Min Range: -1.7421

Max Act: 1.5923. Min Act: -0.0002

Data Index: 646381 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.7421. Min Act: -0.0002

Data Index: 105034 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.6257. Min Act: -0.0002

Data Index: 606888 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.6284. Min Act: -0.0002

Data Index: 174622 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.5105. Min Act: -0.0001

Data Index: 204688 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.5116. Min Act: -0.0002

Data Index: 877830 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.4580. Min Act: -0.0002

Data Index: 345247 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.4948. Min Act: -0.0002

Data Index: 1058801 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.4148. Min Act: -0.0001

Data Index: 970802 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.3159. Min Act: -0.0002

Data Index: 187855 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.3134. Min Act: -0.0002

Data Index: 643679 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.4396. Min Act: -0.0002

Data Index: 827099 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.3958. Min Act: -0.0002

Data Index: 258072 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.4553. Min Act: -0.0001

Data Index: 1200364 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.3739. Min Act: -0.0001

Data Index: 12099 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.3296. Min Act: -0.0002

Data Index: 565004 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.3534. Min Act: -0.0002

Data Index: 429266 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.3911. Min Act: -0.0002

Data Index: 927784 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.3531. Min Act: -0.0002

Data Index: 897771 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 1.7421. Min Range: -1.7421

Max Act: 1.4181. Min Act: -0.0002

Data Index: 708734 (C4 (Web Text))

Max Activating Token Index: 980