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

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

Neuron 123 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4934. Min Range: -2.4934

Max Act: 2.4934. Min Act: -0.0000

Data Index: 1411030 (Python Code)

Max Activating Token Index: 42

Text #1

Max Range: 2.4934. Min Range: -2.4934

Max Act: 1.7455. Min Act: -0.0000

Data Index: 1519147 (Python Code)

Max Activating Token Index: 209

Text #2

Max Range: 2.4934. Min Range: -2.4934

Max Act: 1.4434. Min Act: -0.0000

Data Index: 52917 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 2.4934. Min Range: -2.4934

Max Act: 1.3897. Min Act: -0.0000

Data Index: 1463293 (Python Code)

Max Activating Token Index: 244

Text #4

Max Range: 2.4934. Min Range: -2.4934

Max Act: 1.3565. Min Act: -0.0000

Data Index: 1637119 (Python Code)

Max Activating Token Index: 398

Text #5

Max Range: 2.4934. Min Range: -2.4934

Max Act: 1.3355. Min Act: -0.0000

Data Index: 1598894 (Python Code)

Max Activating Token Index: 901

Text #6

Max Range: 2.4934. Min Range: -2.4934

Max Act: 1.4353. Min Act: -0.0000

Data Index: 1415131 (Python Code)

Max Activating Token Index: 901

Text #7

Max Range: 2.4934. Min Range: -2.4934

Max Act: 1.4886. Min Act: -0.0000

Data Index: 1453301 (Python Code)

Max Activating Token Index: 374

Text #8

Max Range: 2.4934. Min Range: -2.4934

Max Act: 1.3358. Min Act: -0.0000

Data Index: 1374653 (Python Code)

Max Activating Token Index: 724

Text #9

Max Range: 2.4934. Min Range: -2.4934

Max Act: 1.3310. Min Act: -0.0000

Data Index: 1487308 (Python Code)

Max Activating Token Index: 363

Text #10

Max Range: 2.4934. Min Range: -2.4934

Max Act: 1.4917. Min Act: -0.0000

Data Index: 1366557 (Python Code)

Max Activating Token Index: 204

Text #11

Max Range: 2.4934. Min Range: -2.4934

Max Act: 1.3551. Min Act: -0.0000

Data Index: 1461157 (Python Code)

Max Activating Token Index: 557

Text #12

Max Range: 2.4934. Min Range: -2.4934

Max Act: 1.3425. Min Act: -0.0000

Data Index: 1600717 (Python Code)

Max Activating Token Index: 995

Text #13

Max Range: 2.4934. Min Range: -2.4934

Max Act: 1.3385. Min Act: -0.0000

Data Index: 1631300 (Python Code)

Max Activating Token Index: 616

Text #14

Max Range: 2.4934. Min Range: -2.4934

Max Act: 1.3618. Min Act: -0.0000

Data Index: 1538827 (Python Code)

Max Activating Token Index: 717

Text #15

Max Range: 2.4934. Min Range: -2.4934

Max Act: 1.2785. Min Act: -0.0000

Data Index: 994299 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 2.4934. Min Range: -2.4934

Max Act: 1.2633. Min Act: -0.0000

Data Index: 1410481 (Python Code)

Max Activating Token Index: 608

Text #17

Max Range: 2.4934. Min Range: -2.4934

Max Act: 1.2313. Min Act: -0.0000

Data Index: 1651885 (Python Code)

Max Activating Token Index: 66

Text #18

Max Range: 2.4934. Min Range: -2.4934

Max Act: 1.2523. Min Act: -0.0000

Data Index: 1477973 (Python Code)

Max Activating Token Index: 442

Text #19

Max Range: 2.4934. Min Range: -2.4934

Max Act: 1.2876. Min Act: -0.0000

Data Index: 1453068 (Python Code)

Max Activating Token Index: 412