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

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

Neuron 2249 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.6975. Min Act: -0.0000

Data Index: 557512 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.6966. Min Act: -0.0000

Data Index: 820139 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.6252. Min Act: -0.0000

Data Index: 604911 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.6282. Min Act: -0.0000

Data Index: 97641 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.6858. Min Act: -0.0000

Data Index: 61676 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5921. Min Act: -0.0000

Data Index: 845383 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.6077. Min Act: -0.0001

Data Index: 357087 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.6081. Min Act: -0.0000

Data Index: 305944 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5495. Min Act: -0.0000

Data Index: 147425 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5476. Min Act: -0.0001

Data Index: 894715 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5566. Min Act: -0.0001

Data Index: 588201 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5557. Min Act: -0.0001

Data Index: 1193509 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5509. Min Act: -0.0001

Data Index: 1224111 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5467. Min Act: -0.0000

Data Index: 1256230 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5302. Min Act: -0.0001

Data Index: 500362 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5785. Min Act: -0.0000

Data Index: 912830 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5185. Min Act: -0.0000

Data Index: 852683 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5292. Min Act: -0.0000

Data Index: 920629 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1227314 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5229. Min Act: -0.0001

Data Index: 253172 (C4 (Web Text))

Max Activating Token Index: 110