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

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

Neuron 3899 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3572. Min Act: -0.0002

Data Index: 1314064 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3557. Min Act: -0.0002

Data Index: 209322 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3562. Min Act: -0.0003

Data Index: 257376 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3506. Min Act: -0.0002

Data Index: 1209365 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3420. Min Act: -0.0002

Data Index: 854833 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3486. Min Act: -0.0003

Data Index: 194947 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3290. Min Act: -0.0002

Data Index: 399555 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3281. Min Act: -0.0002

Data Index: 481624 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3360. Min Act: -0.0002

Data Index: 730019 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3380. Min Act: -0.0002

Data Index: 923303 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3342. Min Act: -0.0002

Data Index: 1280092 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3331. Min Act: -0.0002

Data Index: 1350010 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3308. Min Act: -0.0002

Data Index: 402726 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3272. Min Act: -0.0002

Data Index: 756638 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3243. Min Act: -0.0002

Data Index: 824988 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3195. Min Act: -0.0002

Data Index: 644914 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3245. Min Act: -0.0002

Data Index: 231003 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3207. Min Act: -0.0003

Data Index: 688059 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3240. Min Act: -0.0002

Data Index: 450406 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3210. Min Act: -0.0002

Data Index: 34298 (C4 (Web Text))

Max Activating Token Index: 437