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

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

Neuron 2632 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2030. Min Range: -1.2030

Max Act: 1.2030. Min Act: -0.0000

Data Index: 1593350 (Python Code)

Max Activating Token Index: 999

Text #1

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.7503. Min Act: -0.0000

Data Index: 1595349 (Python Code)

Max Activating Token Index: 997

Text #2

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.7771. Min Act: -0.0000

Data Index: 1594387 (Python Code)

Max Activating Token Index: 994

Text #3

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.6046. Min Act: 0.0000

Data Index: 1450016 (Python Code)

Max Activating Token Index: 754

Text #4

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.5125. Min Act: -0.0000

Data Index: 355740 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.5310. Min Act: 0.0000

Data Index: 1565578 (Python Code)

Max Activating Token Index: 212

Text #6

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1529258 (Python Code)

Max Activating Token Index: 874

Text #7

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.5061. Min Act: 0.0000

Data Index: 1528991 (Python Code)

Max Activating Token Index: 86

Text #8

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.4635. Min Act: 0.0000

Data Index: 1560080 (Python Code)

Max Activating Token Index: 748

Text #9

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.4256. Min Act: -0.0000

Data Index: 1642199 (Python Code)

Max Activating Token Index: 428

Text #10

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.4535. Min Act: -0.0000

Data Index: 1427595 (Python Code)

Max Activating Token Index: 643

Text #11

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.4309. Min Act: 0.0000

Data Index: 1418923 (Python Code)

Max Activating Token Index: 956

Text #12

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.4490. Min Act: 0.0000

Data Index: 1471282 (Python Code)

Max Activating Token Index: 554

Text #13

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1551368 (Python Code)

Max Activating Token Index: 995

Text #14

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.4676. Min Act: -0.0000

Data Index: 1470467 (Python Code)

Max Activating Token Index: 258

Text #15

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1415552 (Python Code)

Max Activating Token Index: 706

Text #16

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1367822 (Python Code)

Max Activating Token Index: 1010

Text #17

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.3897. Min Act: 0.0000

Data Index: 1611150 (Python Code)

Max Activating Token Index: 964

Text #18

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.3948. Min Act: 0.0000

Data Index: 1615407 (Python Code)

Max Activating Token Index: 1021

Text #19

Max Range: 1.2030. Min Range: -1.2030

Max Act: 0.4293. Min Act: -0.0000

Data Index: 756051 (C4 (Web Text))

Max Activating Token Index: 150