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

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

Neuron 1605 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.3333. Min Act: -0.0001

Data Index: 1640288 (Python Code)

Max Activating Token Index: 418

Text #1

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2937. Min Act: -0.0001

Data Index: 1433389 (Python Code)

Max Activating Token Index: 667

Text #2

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.3136. Min Act: -0.0001

Data Index: 1497592 (Python Code)

Max Activating Token Index: 629

Text #3

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.3088. Min Act: -0.0001

Data Index: 1563993 (Python Code)

Max Activating Token Index: 421

Text #4

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1545169 (Python Code)

Max Activating Token Index: 438

Text #5

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1386502 (Python Code)

Max Activating Token Index: 464

Text #6

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2603. Min Act: -0.0000

Data Index: 129128 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2356. Min Act: -0.0001

Data Index: 1611651 (Python Code)

Max Activating Token Index: 317

Text #8

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2956. Min Act: -0.0001

Data Index: 1589220 (Python Code)

Max Activating Token Index: 694

Text #9

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2618. Min Act: -0.0001

Data Index: 1424630 (Python Code)

Max Activating Token Index: 155

Text #10

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2466. Min Act: -0.0001

Data Index: 1611384 (Python Code)

Max Activating Token Index: 84

Text #11

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2471. Min Act: -0.0001

Data Index: 1497838 (Python Code)

Max Activating Token Index: 574

Text #12

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2529. Min Act: -0.0001

Data Index: 1466027 (Python Code)

Max Activating Token Index: 200

Text #13

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2600. Min Act: -0.0001

Data Index: 1433480 (Python Code)

Max Activating Token Index: 914

Text #14

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2523. Min Act: -0.0000

Data Index: 1607228 (Python Code)

Max Activating Token Index: 217

Text #15

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2417. Min Act: -0.0001

Data Index: 1532128 (Python Code)

Max Activating Token Index: 477

Text #16

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2326. Min Act: -0.0001

Data Index: 1514533 (Python Code)

Max Activating Token Index: 182

Text #17

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2400. Min Act: -0.0000

Data Index: 1581137 (Python Code)

Max Activating Token Index: 468

Text #18

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2212. Min Act: -0.0000

Data Index: 17101 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2241. Min Act: -0.0001

Data Index: 1484201 (Python Code)

Max Activating Token Index: 319