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

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

Neuron 2607 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.2077. Min Act: -0.0000

Data Index: 996537 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1910. Min Act: -0.0000

Data Index: 721529 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1564. Min Act: -0.0000

Data Index: 946367 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1648. Min Act: -0.0000

Data Index: 758010 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1539. Min Act: -0.0000

Data Index: 272476 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1456. Min Act: -0.0000

Data Index: 849548 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1450. Min Act: -0.0000

Data Index: 586543 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1397. Min Act: -0.0000

Data Index: 1312600 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1476. Min Act: -0.0000

Data Index: 400076 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1420. Min Act: -0.0000

Data Index: 663875 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1245876 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1180486 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1326. Min Act: -0.0000

Data Index: 328632 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1363. Min Act: -0.0000

Data Index: 599934 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1010652 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1477. Min Act: -0.0000

Data Index: 457789 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1317. Min Act: -0.0000

Data Index: 931436 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1393. Min Act: -0.0000

Data Index: 390117 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1250. Min Act: -0.0000

Data Index: 676692 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1274447 (C4 (Web Text))

Max Activating Token Index: 391