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

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

Neuron 2958 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: 1.0856. Min Range: -1.0856

Max Act: 1.0856. Min Act: -0.0001

Data Index: 1241154 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0614. Min Act: -0.0001

Data Index: 896200 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.9592. Min Act: -0.0001

Data Index: 1331082 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0114. Min Act: -0.0001

Data Index: 1327536 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.9929. Min Act: -0.0001

Data Index: 491699 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.9842. Min Act: -0.0001

Data Index: 1045308 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.9810. Min Act: -0.0001

Data Index: 878385 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.9421. Min Act: -0.0001

Data Index: 1197117 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.9746. Min Act: -0.0001

Data Index: 168218 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.8969. Min Act: -0.0001

Data Index: 366719 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.8910. Min Act: -0.0001

Data Index: 1265718 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.8818. Min Act: -0.0001

Data Index: 1238868 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.7600. Min Act: -0.0001

Data Index: 1192002 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.6369. Min Act: -0.0001

Data Index: 1140884 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.7110. Min Act: -0.0001

Data Index: 1498276 (Python Code)

Max Activating Token Index: 43

Text #15

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.6566. Min Act: -0.0001

Data Index: 508671 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.6553. Min Act: -0.0001

Data Index: 1232348 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.6715. Min Act: -0.0001

Data Index: 675734 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.6458. Min Act: -0.0001

Data Index: 1309296 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.6453. Min Act: -0.0001

Data Index: 1067923 (C4 (Web Text))

Max Activating Token Index: 167