Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1662 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3415. Min Act: -0.0000

Data Index: 404897 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2948. Min Act: -0.0000

Data Index: 171201 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3048. Min Act: -0.0000

Data Index: 936480 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3159. Min Act: -0.0000

Data Index: 876826 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2528. Min Act: -0.0000

Data Index: 111852 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2632. Min Act: -0.0000

Data Index: 885203 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1486666 (Python Code)

Max Activating Token Index: 838

Text #7

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2692. Min Act: -0.0000

Data Index: 918073 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2503. Min Act: -0.0000

Data Index: 1175763 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2374. Min Act: -0.0000

Data Index: 1356210 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2387. Min Act: -0.0000

Data Index: 48565 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2278. Min Act: -0.0000

Data Index: 432670 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2513. Min Act: -0.0000

Data Index: 301322 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2517. Min Act: -0.0000

Data Index: 988917 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2167. Min Act: -0.0000

Data Index: 226702 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2334. Min Act: -0.0000

Data Index: 1634706 (Python Code)

Max Activating Token Index: 560

Text #16

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2259. Min Act: -0.0000

Data Index: 91313 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1145774 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2260. Min Act: -0.0000

Data Index: 925439 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2330. Min Act: -0.0000

Data Index: 950587 (C4 (Web Text))

Max Activating Token Index: 500