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

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

Neuron 545 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: 2.8412. Min Range: -2.8412

Max Act: 2.8412. Min Act: -0.0002

Data Index: 1167666 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 2.8412. Min Range: -2.8412

Max Act: 2.6962. Min Act: -0.0002

Data Index: 21698 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 2.8412. Min Range: -2.8412

Max Act: 2.5098. Min Act: -0.0002

Data Index: 212487 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 2.8412. Min Range: -2.8412

Max Act: 2.3778. Min Act: -0.0002

Data Index: 237071 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 2.8412. Min Range: -2.8412

Max Act: 2.3712. Min Act: -0.0002

Data Index: 234698 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 2.8412. Min Range: -2.8412

Max Act: 2.2294. Min Act: -0.0002

Data Index: 1600076 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 2.8412. Min Range: -2.8412

Max Act: 2.2109. Min Act: -0.0002

Data Index: 502139 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 2.8412. Min Range: -2.8412

Max Act: 2.2110. Min Act: -0.0002

Data Index: 273997 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 2.8412. Min Range: -2.8412

Max Act: 2.0176. Min Act: -0.0002

Data Index: 190699 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 2.8412. Min Range: -2.8412

Max Act: 2.0514. Min Act: -0.0002

Data Index: 390725 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 2.8412. Min Range: -2.8412

Max Act: 1.9847. Min Act: -0.0002

Data Index: 1267165 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 2.8412. Min Range: -2.8412

Max Act: 1.9863. Min Act: -0.0002

Data Index: 910713 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 2.8412. Min Range: -2.8412

Max Act: 2.0564. Min Act: -0.0002

Data Index: 1656140 (Python Code)

Max Activating Token Index: 770

Text #13

Max Range: 2.8412. Min Range: -2.8412

Max Act: 1.9768. Min Act: -0.0002

Data Index: 1312288 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 2.8412. Min Range: -2.8412

Max Act: 1.9768. Min Act: -0.0002

Data Index: 1064676 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 2.8412. Min Range: -2.8412

Max Act: 1.9768. Min Act: -0.0002

Data Index: 969314 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 2.8412. Min Range: -2.8412

Max Act: 1.9349. Min Act: -0.0002

Data Index: 924979 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 2.8412. Min Range: -2.8412

Max Act: 1.9291. Min Act: -0.0002

Data Index: 828268 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 2.8412. Min Range: -2.8412

Max Act: 1.9249. Min Act: -0.0002

Data Index: 581034 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 2.8412. Min Range: -2.8412

Max Act: 1.9073. Min Act: -0.0002

Data Index: 1366228 (Python Code)

Max Activating Token Index: 993