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

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

Neuron 6089 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0493. Min Act: -0.0000

Data Index: 730535 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0348. Min Act: -0.0000

Data Index: 1081175 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0349. Min Act: 0.0000

Data Index: 1608105 (Python Code)

Max Activating Token Index: 539

Text #3

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0364. Min Act: -0.0000

Data Index: 1437940 (Python Code)

Max Activating Token Index: 79

Text #4

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0358. Min Act: -0.0000

Data Index: 319241 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0322. Min Act: -0.0000

Data Index: 967311 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0342. Min Act: -0.0000

Data Index: 1648350 (Python Code)

Max Activating Token Index: 943

Text #7

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0340. Min Act: -0.0000

Data Index: 278599 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0314. Min Act: -0.0000

Data Index: 1560229 (Python Code)

Max Activating Token Index: 801

Text #9

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0335. Min Act: -0.0000

Data Index: 1427901 (Python Code)

Max Activating Token Index: 248

Text #10

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0333. Min Act: -0.0000

Data Index: 694615 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0343. Min Act: -0.0000

Data Index: 1504766 (Python Code)

Max Activating Token Index: 323

Text #12

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1350156 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0313. Min Act: -0.0000

Data Index: 80142 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0322. Min Act: -0.0000

Data Index: 759571 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0314. Min Act: -0.0000

Data Index: 1280776 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0324. Min Act: -0.0000

Data Index: 740499 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0331. Min Act: -0.0000

Data Index: 1447853 (Python Code)

Max Activating Token Index: 915

Text #18

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0305. Min Act: -0.0000

Data Index: 1267762 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.0493. Min Range: -0.0493

Max Act: 0.0304. Min Act: -0.0000

Data Index: 508387 (C4 (Web Text))

Max Activating Token Index: 144