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

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

Neuron 3744 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2565. Min Act: -0.0001

Data Index: 1583211 (Python Code)

Max Activating Token Index: 686

Text #1

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2546. Min Act: -0.0001

Data Index: 1523610 (Python Code)

Max Activating Token Index: 693

Text #2

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2596. Min Act: -0.0001

Data Index: 1418999 (Python Code)

Max Activating Token Index: 778

Text #3

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2535. Min Act: -0.0001

Data Index: 1656059 (Python Code)

Max Activating Token Index: 91

Text #4

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2481. Min Act: -0.0001

Data Index: 1464823 (Python Code)

Max Activating Token Index: 784

Text #5

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2479. Min Act: -0.0001

Data Index: 1602805 (Python Code)

Max Activating Token Index: 924

Text #6

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2458. Min Act: -0.0001

Data Index: 1457499 (Python Code)

Max Activating Token Index: 681

Text #7

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2478. Min Act: -0.0001

Data Index: 1615783 (Python Code)

Max Activating Token Index: 129

Text #8

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2487. Min Act: -0.0001

Data Index: 1617288 (Python Code)

Max Activating Token Index: 27

Text #9

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2439. Min Act: -0.0001

Data Index: 1524300 (Python Code)

Max Activating Token Index: 149

Text #10

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2340. Min Act: -0.0001

Data Index: 1532916 (Python Code)

Max Activating Token Index: 997

Text #11

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2388. Min Act: -0.0001

Data Index: 1385827 (Python Code)

Max Activating Token Index: 886

Text #12

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2297. Min Act: -0.0001

Data Index: 1484983 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2319. Min Act: -0.0001

Data Index: 1363740 (Python Code)

Max Activating Token Index: 921

Text #14

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2322. Min Act: -0.0001

Data Index: 1455553 (Python Code)

Max Activating Token Index: 721

Text #15

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2320. Min Act: -0.0001

Data Index: 1402538 (Python Code)

Max Activating Token Index: 67

Text #16

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2304. Min Act: -0.0001

Data Index: 1386979 (Python Code)

Max Activating Token Index: 228

Text #17

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2326. Min Act: -0.0001

Data Index: 1374461 (Python Code)

Max Activating Token Index: 46

Text #18

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2264. Min Act: -0.0001

Data Index: 1564677 (Python Code)

Max Activating Token Index: 898

Text #19

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2241. Min Act: -0.0001

Data Index: 1426467 (Python Code)

Max Activating Token Index: 519