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

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

Neuron 3920 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.4096. Min Act: -0.0000

Data Index: 1230643 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2975. Min Act: -0.0000

Data Index: 195007 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2448. Min Act: -0.0000

Data Index: 131791 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2629. Min Act: -0.0000

Data Index: 1623627 (Python Code)

Max Activating Token Index: 489

Text #4

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1507032 (Python Code)

Max Activating Token Index: 100

Text #5

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1379865 (Python Code)

Max Activating Token Index: 508

Text #6

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1541457 (Python Code)

Max Activating Token Index: 847

Text #7

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2540. Min Act: -0.0000

Data Index: 221872 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2458. Min Act: -0.0000

Data Index: 625487 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2474. Min Act: -0.0000

Data Index: 1375263 (Python Code)

Max Activating Token Index: 416

Text #10

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2387. Min Act: -0.0000

Data Index: 198406 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2406. Min Act: -0.0000

Data Index: 590559 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2410. Min Act: -0.0000

Data Index: 857526 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2310. Min Act: -0.0000

Data Index: 651934 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2492. Min Act: -0.0000

Data Index: 810308 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2398. Min Act: -0.0000

Data Index: 524167 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2305. Min Act: -0.0000

Data Index: 630693 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2294. Min Act: -0.0000

Data Index: 522703 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2436. Min Act: -0.0000

Data Index: 1638710 (Python Code)

Max Activating Token Index: 191

Text #19

Max Range: 0.4096. Min Range: -0.4096

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1422422 (Python Code)

Max Activating Token Index: 219