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

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

Neuron 4710 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.9282. Min Act: -0.0000

Data Index: 484831 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.6307. Min Act: -0.0000

Data Index: 335647 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.6414. Min Act: -0.0000

Data Index: 154948 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.5240. Min Act: -0.0000

Data Index: 839451 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.5018. Min Act: -0.0000

Data Index: 115918 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.5885. Min Act: -0.0000

Data Index: 356013 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.5564. Min Act: -0.0000

Data Index: 651382 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.6424. Min Act: -0.0000

Data Index: 724993 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.5489. Min Act: -0.0000

Data Index: 114097 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.5197. Min Act: -0.0000

Data Index: 538768 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.4519. Min Act: -0.0000

Data Index: 1060988 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.4194. Min Act: -0.0000

Data Index: 1259818 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.4066. Min Act: -0.0000

Data Index: 1334710 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.3649. Min Act: -0.0000

Data Index: 46629 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.3785. Min Act: -0.0000

Data Index: 1307314 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.3632. Min Act: -0.0000

Data Index: 719555 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.3509. Min Act: -0.0000

Data Index: 861358 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.2230. Min Act: -0.0000

Data Index: 627003 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.3085. Min Act: -0.0000

Data Index: 440493 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 1.9282. Min Range: -1.9282

Max Act: 1.2739. Min Act: -0.0000

Data Index: 1262110 (C4 (Web Text))

Max Activating Token Index: 21