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

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

Neuron 353 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.2320. Min Act: -0.0001

Data Index: 1529539 (Python Code)

Max Activating Token Index: 873

Text #1

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.2313. Min Act: -0.0001

Data Index: 1583393 (Python Code)

Max Activating Token Index: 792

Text #2

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.2282. Min Act: -0.0001

Data Index: 1541551 (Python Code)

Max Activating Token Index: 184

Text #3

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.2027. Min Act: -0.0001

Data Index: 1432924 (Python Code)

Max Activating Token Index: 50

Text #4

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1671. Min Act: -0.0001

Data Index: 1614254 (Python Code)

Max Activating Token Index: 428

Text #5

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1654. Min Act: -0.0001

Data Index: 1383119 (Python Code)

Max Activating Token Index: 131

Text #6

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1673. Min Act: -0.0001

Data Index: 1553392 (Python Code)

Max Activating Token Index: 86

Text #7

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1629. Min Act: -0.0001

Data Index: 1612747 (Python Code)

Max Activating Token Index: 129

Text #8

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1571. Min Act: -0.0001

Data Index: 1441229 (Python Code)

Max Activating Token Index: 396

Text #9

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1367921 (Python Code)

Max Activating Token Index: 206

Text #10

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1536. Min Act: -0.0001

Data Index: 1629669 (Python Code)

Max Activating Token Index: 957

Text #11

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1603. Min Act: -0.0001

Data Index: 1605041 (Python Code)

Max Activating Token Index: 1011

Text #12

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1494. Min Act: -0.0001

Data Index: 1479258 (Python Code)

Max Activating Token Index: 404

Text #13

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1385. Min Act: -0.0001

Data Index: 1612668 (Python Code)

Max Activating Token Index: 835

Text #14

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1486. Min Act: -0.0001

Data Index: 1498054 (Python Code)

Max Activating Token Index: 42

Text #15

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1500522 (Python Code)

Max Activating Token Index: 535

Text #16

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1377. Min Act: -0.0001

Data Index: 1641830 (Python Code)

Max Activating Token Index: 11

Text #17

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1345. Min Act: -0.0001

Data Index: 1444851 (Python Code)

Max Activating Token Index: 994

Text #18

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1555864 (Python Code)

Max Activating Token Index: 972

Text #19

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1402. Min Act: -0.0001

Data Index: 1578114 (Python Code)

Max Activating Token Index: 182