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

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

Neuron 5096 in Layer 0

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: 0.2519. Min Range: -0.2519

Max Act: 0.2519. Min Act: -0.0001

Data Index: 653875 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2501. Min Act: -0.0001

Data Index: 131789 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2336. Min Act: -0.0001

Data Index: 676166 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2361. Min Act: -0.0001

Data Index: 30931 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2359. Min Act: -0.0001

Data Index: 1312051 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2328. Min Act: -0.0001

Data Index: 1222939 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2336. Min Act: -0.0001

Data Index: 923416 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2324. Min Act: -0.0001

Data Index: 329645 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2310. Min Act: -0.0002

Data Index: 853785 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2239. Min Act: -0.0001

Data Index: 169065 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2276. Min Act: -0.0001

Data Index: 456442 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2287. Min Act: -0.0001

Data Index: 237855 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2309. Min Act: -0.0001

Data Index: 65572 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2255. Min Act: -0.0001

Data Index: 1013859 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2259. Min Act: -0.0001

Data Index: 968871 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2231. Min Act: -0.0001

Data Index: 1648964 (Python Code)

Max Activating Token Index: 664

Text #16

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2276. Min Act: -0.0001

Data Index: 788142 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2213. Min Act: -0.0001

Data Index: 111312 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2216. Min Act: -0.0001

Data Index: 664287 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.2519. Min Range: -0.2519

Max Act: 0.2253. Min Act: -0.0001

Data Index: 316882 (C4 (Web Text))

Max Activating Token Index: 662