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

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

Neuron 4627 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: 1.0793. Min Range: -1.0793

Max Act: 1.0300. Min Act: -0.0000

Data Index: 1561486 (Python Code)

Max Activating Token Index: 944

Text #1

Max Range: 1.0793. Min Range: -1.0793

Max Act: 1.0654. Min Act: -0.0000

Data Index: 1564228 (Python Code)

Max Activating Token Index: 220

Text #2

Max Range: 1.0793. Min Range: -1.0793

Max Act: 1.0344. Min Act: -0.0000

Data Index: 1623532 (Python Code)

Max Activating Token Index: 413

Text #3

Max Range: 1.0793. Min Range: -1.0793

Max Act: 1.0793. Min Act: -0.0000

Data Index: 271320 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1499119 (Python Code)

Max Activating Token Index: 970

Text #5

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.8020. Min Act: -0.0000

Data Index: 1611476 (Python Code)

Max Activating Token Index: 836

Text #6

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.8227. Min Act: -0.0000

Data Index: 1615791 (Python Code)

Max Activating Token Index: 306

Text #7

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1514409 (Python Code)

Max Activating Token Index: 110

Text #8

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.8111. Min Act: -0.0000

Data Index: 781008 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1420059 (Python Code)

Max Activating Token Index: 947

Text #10

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.7885. Min Act: -0.0000

Data Index: 1548062 (Python Code)

Max Activating Token Index: 53

Text #11

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.7459. Min Act: -0.0000

Data Index: 502534 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.7408. Min Act: -0.0000

Data Index: 1435525 (Python Code)

Max Activating Token Index: 828

Text #13

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.7344. Min Act: -0.0000

Data Index: 1395997 (Python Code)

Max Activating Token Index: 325

Text #14

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.7601. Min Act: -0.0000

Data Index: 1627439 (Python Code)

Max Activating Token Index: 227

Text #15

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.7493. Min Act: -0.0000

Data Index: 1625472 (Python Code)

Max Activating Token Index: 806

Text #16

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.6647. Min Act: -0.0000

Data Index: 1655998 (Python Code)

Max Activating Token Index: 378

Text #17

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1647392 (Python Code)

Max Activating Token Index: 78

Text #18

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.7237. Min Act: -0.0000

Data Index: 1368289 (Python Code)

Max Activating Token Index: 294

Text #19

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1355482 (C4 (Web Text))

Max Activating Token Index: 821