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

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

Neuron 3316 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.4397. Min Act: -0.0001

Data Index: 1430351 (Python Code)

Max Activating Token Index: 24

Text #1

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.4360. Min Act: -0.0001

Data Index: 1445224 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.2519. Min Act: -0.0001

Data Index: 1539002 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.1044. Min Act: -0.0001

Data Index: 1380365 (Python Code)

Max Activating Token Index: 181

Text #4

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.9666. Min Act: -0.0001

Data Index: 377476 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.9666. Min Act: -0.0001

Data Index: 457605 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.0362. Min Act: -0.0001

Data Index: 1374665 (Python Code)

Max Activating Token Index: 59

Text #7

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.8866. Min Act: -0.0001

Data Index: 3431 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.0155. Min Act: -0.0001

Data Index: 499766 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.0107. Min Act: -0.0001

Data Index: 247935 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.9376. Min Act: -0.0001

Data Index: 1607393 (Python Code)

Max Activating Token Index: 919

Text #11

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.0418. Min Act: -0.0001

Data Index: 1551632 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.9368. Min Act: -0.0001

Data Index: 1261615 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.9911. Min Act: -0.0001

Data Index: 698636 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.9361. Min Act: -0.0001

Data Index: 1513576 (Python Code)

Max Activating Token Index: 76

Text #15

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.9961. Min Act: -0.0001

Data Index: 515579 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.0235. Min Act: -0.0001

Data Index: 385003 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.9571. Min Act: -0.0001

Data Index: 1433953 (Python Code)

Max Activating Token Index: 265

Text #18

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.9377. Min Act: -0.0001

Data Index: 1537069 (Python Code)

Max Activating Token Index: 92

Text #19

Max Range: 1.4397. Min Range: -1.4397

Max Act: 0.9327. Min Act: -0.0001

Data Index: 1375994 (Python Code)

Max Activating Token Index: 261