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

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

Neuron 3196 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: 1.6366. Min Range: -1.6366

Max Act: 1.6366. Min Act: -0.0000

Data Index: 1165708 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.5856. Min Act: -0.0000

Data Index: 722014 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.4671. Min Act: -0.0000

Data Index: 56818 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 1.6366. Min Range: -1.6366

Max Act: 1.3975. Min Act: -0.0000

Data Index: 146447 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 1.6366. Min Range: -1.6366

Max Act: 0.9676. Min Act: -0.0000

Data Index: 1078522 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 1.6366. Min Range: -1.6366

Max Act: 0.8853. Min Act: -0.0000

Data Index: 879938 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 1.6366. Min Range: -1.6366

Max Act: 0.8168. Min Act: -0.0000

Data Index: 626606 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 1.6366. Min Range: -1.6366

Max Act: 0.7882. Min Act: -0.0000

Data Index: 236914 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 1.6366. Min Range: -1.6366

Max Act: 0.7697. Min Act: -0.0000

Data Index: 145895 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 1.6366. Min Range: -1.6366

Max Act: 0.7242. Min Act: -0.0000

Data Index: 786645 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 1.6366. Min Range: -1.6366

Max Act: 0.7174. Min Act: -0.0000

Data Index: 607478 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 1.6366. Min Range: -1.6366

Max Act: 0.6959. Min Act: -0.0000

Data Index: 1132465 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 1.6366. Min Range: -1.6366

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1188459 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 1.6366. Min Range: -1.6366

Max Act: 0.6656. Min Act: -0.0000

Data Index: 625039 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 1.6366. Min Range: -1.6366

Max Act: 0.6642. Min Act: -0.0000

Data Index: 1310798 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 1.6366. Min Range: -1.6366

Max Act: 0.6516. Min Act: -0.0000

Data Index: 655479 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 1.6366. Min Range: -1.6366

Max Act: 0.6756. Min Act: -0.0000

Data Index: 1231496 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 1.6366. Min Range: -1.6366

Max Act: 0.6531. Min Act: -0.0000

Data Index: 192836 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 1.6366. Min Range: -1.6366

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1174517 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 1.6366. Min Range: -1.6366

Max Act: 0.6648. Min Act: -0.0000

Data Index: 436252 (C4 (Web Text))

Max Activating Token Index: 943