Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2567 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0221. Min Range: -1.0221

Max Act: 1.0221. Min Act: -0.0002

Data Index: 77248 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 1.0221. Min Range: -1.0221

Max Act: 0.8876. Min Act: -0.0002

Data Index: 469761 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 1.0221. Min Range: -1.0221

Max Act: 0.8580. Min Act: -0.0002

Data Index: 615628 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 1.0221. Min Range: -1.0221

Max Act: 0.7824. Min Act: -0.0002

Data Index: 908023 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 1.0221. Min Range: -1.0221

Max Act: 0.8652. Min Act: -0.0002

Data Index: 1047199 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 1.0221. Min Range: -1.0221

Max Act: 0.8084. Min Act: -0.0002

Data Index: 60913 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 1.0221. Min Range: -1.0221

Max Act: 0.7659. Min Act: -0.0002

Data Index: 1313141 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 1.0221. Min Range: -1.0221

Max Act: 0.8349. Min Act: -0.0002

Data Index: 700035 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 1.0221. Min Range: -1.0221

Max Act: 0.8984. Min Act: -0.0002

Data Index: 91641 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 1.0221. Min Range: -1.0221

Max Act: 0.8257. Min Act: -0.0002

Data Index: 1333840 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 1.0221. Min Range: -1.0221

Max Act: 0.8231. Min Act: -0.0002

Data Index: 107502 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 1.0221. Min Range: -1.0221

Max Act: 0.8155. Min Act: -0.0002

Data Index: 270014 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 1.0221. Min Range: -1.0221

Max Act: 0.8089. Min Act: -0.0002

Data Index: 413227 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 1.0221. Min Range: -1.0221

Max Act: 0.8037. Min Act: -0.0002

Data Index: 19568 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 1.0221. Min Range: -1.0221

Max Act: 0.8040. Min Act: -0.0002

Data Index: 626594 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 1.0221. Min Range: -1.0221

Max Act: 0.8080. Min Act: -0.0002

Data Index: 573532 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 1.0221. Min Range: -1.0221

Max Act: 0.7349. Min Act: -0.0002

Data Index: 1280260 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 1.0221. Min Range: -1.0221

Max Act: 0.7979. Min Act: -0.0002

Data Index: 678001 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 1.0221. Min Range: -1.0221

Max Act: 0.7871. Min Act: -0.0002

Data Index: 598639 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 1.0221. Min Range: -1.0221

Max Act: 0.7252. Min Act: -0.0002

Data Index: 334183 (C4 (Web Text))

Max Activating Token Index: 851