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

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

Neuron 4779 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: 1.0143. Min Range: -1.0143

Max Act: 1.0143. Min Act: -0.0002

Data Index: 1084683 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.8871. Min Act: -0.0002

Data Index: 217073 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.7939. Min Act: -0.0002

Data Index: 302170 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.7722. Min Act: -0.0002

Data Index: 1112229 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.8777. Min Act: -0.0002

Data Index: 343554 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.7563. Min Act: -0.0002

Data Index: 928675 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.8046. Min Act: -0.0002

Data Index: 467667 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.6432. Min Act: -0.0002

Data Index: 287197 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.7282. Min Act: -0.0002

Data Index: 806204 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.6963. Min Act: -0.0002

Data Index: 39196 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.7203. Min Act: -0.0002

Data Index: 815479 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.5939. Min Act: -0.0002

Data Index: 1183879 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.6176. Min Act: -0.0002

Data Index: 1073424 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.6547. Min Act: -0.0002

Data Index: 988261 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.6294. Min Act: -0.0002

Data Index: 636911 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.6631. Min Act: -0.0002

Data Index: 1113761 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.5866. Min Act: -0.0002

Data Index: 401493 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.5626. Min Act: -0.0002

Data Index: 1100394 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.5304. Min Act: -0.0002

Data Index: 1272435 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.6340. Min Act: -0.0002

Data Index: 709099 (C4 (Web Text))

Max Activating Token Index: 38