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

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

Neuron 3649 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: 0.0366. Min Range: -0.0366

Max Act: 0.0366. Min Act: -0.0001

Data Index: 887264 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1361532 (Python Code)

Max Activating Token Index: 634

Text #2

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0343. Min Act: -0.0001

Data Index: 1443727 (Python Code)

Max Activating Token Index: 889

Text #3

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0347. Min Act: -0.0001

Data Index: 146337 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0340. Min Act: -0.0001

Data Index: 805114 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1441437 (Python Code)

Max Activating Token Index: 624

Text #6

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0326. Min Act: -0.0001

Data Index: 337297 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1462380 (Python Code)

Max Activating Token Index: 67

Text #8

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0320. Min Act: -0.0001

Data Index: 1334777 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0311. Min Act: -0.0001

Data Index: 566930 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0316. Min Act: -0.0001

Data Index: 1181419 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0309. Min Act: -0.0001

Data Index: 361342 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0310. Min Act: -0.0001

Data Index: 1486629 (Python Code)

Max Activating Token Index: 65

Text #13

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0308. Min Act: -0.0001

Data Index: 689084 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0307. Min Act: -0.0001

Data Index: 728131 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0301. Min Act: -0.0001

Data Index: 1162754 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1305081 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0299. Min Act: -0.0001

Data Index: 1520548 (Python Code)

Max Activating Token Index: 536

Text #18

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0300. Min Act: -0.0001

Data Index: 47867 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0298. Min Act: -0.0001

Data Index: 718035 (C4 (Web Text))

Max Activating Token Index: 813