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

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

Neuron 986 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.9618. Min Act: -0.0001

Data Index: 820976 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.8291. Min Act: -0.0001

Data Index: 1243433 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.6869. Min Act: -0.0001

Data Index: 34764 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.6260. Min Act: -0.0001

Data Index: 134251 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.6741. Min Act: -0.0001

Data Index: 196646 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.6210. Min Act: -0.0001

Data Index: 1335739 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.6047. Min Act: -0.0001

Data Index: 525175 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.6475. Min Act: -0.0001

Data Index: 294840 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.6254. Min Act: -0.0001

Data Index: 61518 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.5836. Min Act: -0.0001

Data Index: 1104878 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.6137. Min Act: -0.0001

Data Index: 759635 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.5458. Min Act: -0.0001

Data Index: 266837 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.5414. Min Act: -0.0001

Data Index: 189080 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.6125. Min Act: -0.0001

Data Index: 622048 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.5660. Min Act: -0.0001

Data Index: 969463 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.4088. Min Act: -0.0001

Data Index: 482619 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.4889. Min Act: -0.0001

Data Index: 646164 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.4778. Min Act: -0.0001

Data Index: 408276 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.3966. Min Act: -0.0001

Data Index: 640537 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 1.9618. Min Range: -1.9618

Max Act: 1.5181. Min Act: -0.0001

Data Index: 1277070 (C4 (Web Text))

Max Activating Token Index: 238