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

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

Neuron 3973 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6438. Min Range: -2.6438

Max Act: 2.5347. Min Act: -0.0000

Data Index: 1510500 (Python Code)

Max Activating Token Index: 508

Text #1

Max Range: 2.6438. Min Range: -2.6438

Max Act: 2.6438. Min Act: -0.0000

Data Index: 1409238 (Python Code)

Max Activating Token Index: 780

Text #2

Max Range: 2.6438. Min Range: -2.6438

Max Act: 2.1746. Min Act: -0.0000

Data Index: 1488496 (Python Code)

Max Activating Token Index: 662

Text #3

Max Range: 2.6438. Min Range: -2.6438

Max Act: 2.2116. Min Act: -0.0000

Data Index: 1486701 (Python Code)

Max Activating Token Index: 266

Text #4

Max Range: 2.6438. Min Range: -2.6438

Max Act: 2.0771. Min Act: -0.0000

Data Index: 1483007 (Python Code)

Max Activating Token Index: 947

Text #5

Max Range: 2.6438. Min Range: -2.6438

Max Act: 1.9232. Min Act: -0.0000

Data Index: 1618282 (Python Code)

Max Activating Token Index: 975

Text #6

Max Range: 2.6438. Min Range: -2.6438

Max Act: 2.0658. Min Act: -0.0000

Data Index: 1448389 (Python Code)

Max Activating Token Index: 54

Text #7

Max Range: 2.6438. Min Range: -2.6438

Max Act: 2.1553. Min Act: -0.0000

Data Index: 1466431 (Python Code)

Max Activating Token Index: 919

Text #8

Max Range: 2.6438. Min Range: -2.6438

Max Act: 1.9148. Min Act: -0.0000

Data Index: 1374747 (Python Code)

Max Activating Token Index: 900

Text #9

Max Range: 2.6438. Min Range: -2.6438

Max Act: 2.0078. Min Act: -0.0000

Data Index: 1555729 (Python Code)

Max Activating Token Index: 131

Text #10

Max Range: 2.6438. Min Range: -2.6438

Max Act: 1.8044. Min Act: -0.0000

Data Index: 1656690 (Python Code)

Max Activating Token Index: 971

Text #11

Max Range: 2.6438. Min Range: -2.6438

Max Act: 1.8260. Min Act: -0.0000

Data Index: 1397895 (Python Code)

Max Activating Token Index: 657

Text #12

Max Range: 2.6438. Min Range: -2.6438

Max Act: 1.9880. Min Act: -0.0000

Data Index: 1372519 (Python Code)

Max Activating Token Index: 421

Text #13

Max Range: 2.6438. Min Range: -2.6438

Max Act: 1.8623. Min Act: -0.0000

Data Index: 1439405 (Python Code)

Max Activating Token Index: 201

Text #14

Max Range: 2.6438. Min Range: -2.6438

Max Act: 1.8399. Min Act: -0.0000

Data Index: 1656367 (Python Code)

Max Activating Token Index: 105

Text #15

Max Range: 2.6438. Min Range: -2.6438

Max Act: 1.7575. Min Act: -0.0000

Data Index: 1444765 (Python Code)

Max Activating Token Index: 643

Text #16

Max Range: 2.6438. Min Range: -2.6438

Max Act: 1.7235. Min Act: -0.0000

Data Index: 1597138 (Python Code)

Max Activating Token Index: 960

Text #17

Max Range: 2.6438. Min Range: -2.6438

Max Act: 1.7024. Min Act: -0.0000

Data Index: 1518641 (Python Code)

Max Activating Token Index: 344

Text #18

Max Range: 2.6438. Min Range: -2.6438

Max Act: 1.8131. Min Act: -0.0000

Data Index: 1614289 (Python Code)

Max Activating Token Index: 800

Text #19

Max Range: 2.6438. Min Range: -2.6438

Max Act: 1.8794. Min Act: -0.0000

Data Index: 1367528 (Python Code)

Max Activating Token Index: 347