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

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

Neuron 1827 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.4174. Min Act: 0.0000

Data Index: 1138442 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.4017. Min Act: 0.0000

Data Index: 410701 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3775. Min Act: 0.0000

Data Index: 985430 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3693. Min Act: 0.0000

Data Index: 1064964 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3405. Min Act: 0.0000

Data Index: 100336 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3382. Min Act: 0.0000

Data Index: 509833 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3578. Min Act: 0.0001

Data Index: 1003814 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3563. Min Act: 0.0000

Data Index: 391634 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3794. Min Act: 0.0000

Data Index: 1173636 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3569. Min Act: 0.0002

Data Index: 968113 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1245951 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3512. Min Act: 0.0000

Data Index: 1321945 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3467. Min Act: 0.0001

Data Index: 615718 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3406. Min Act: 0.0001

Data Index: 430079 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1082951 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3369. Min Act: 0.0000

Data Index: 734472 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3383. Min Act: 0.0000

Data Index: 868830 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1212918 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3370. Min Act: -0.0000

Data Index: 567427 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3380. Min Act: -0.0000

Data Index: 80941 (C4 (Web Text))

Max Activating Token Index: 908