Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3974 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0621. Min Act: -0.0001

Data Index: 1455350 (Python Code)

Max Activating Token Index: 234

Text #1

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0565. Min Act: -0.0001

Data Index: 662039 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0509. Min Act: -0.0001

Data Index: 1388952 (Python Code)

Max Activating Token Index: 180

Text #3

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0514. Min Act: -0.0001

Data Index: 1584135 (Python Code)

Max Activating Token Index: 80

Text #4

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0485. Min Act: -0.0001

Data Index: 1653008 (Python Code)

Max Activating Token Index: 423

Text #5

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0450. Min Act: -0.0001

Data Index: 1444044 (Python Code)

Max Activating Token Index: 981

Text #6

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0474. Min Act: -0.0001

Data Index: 1468933 (Python Code)

Max Activating Token Index: 338

Text #7

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0447. Min Act: -0.0001

Data Index: 1062037 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0462. Min Act: -0.0001

Data Index: 1598104 (Python Code)

Max Activating Token Index: 516

Text #9

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0471. Min Act: -0.0001

Data Index: 1403087 (Python Code)

Max Activating Token Index: 611

Text #10

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0446. Min Act: -0.0001

Data Index: 1613265 (Python Code)

Max Activating Token Index: 556

Text #11

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0421. Min Act: -0.0001

Data Index: 1390044 (Python Code)

Max Activating Token Index: 417

Text #12

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1304752 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1618428 (Python Code)

Max Activating Token Index: 949

Text #14

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0421. Min Act: -0.0001

Data Index: 1403476 (Python Code)

Max Activating Token Index: 565

Text #15

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0416. Min Act: -0.0001

Data Index: 1434309 (Python Code)

Max Activating Token Index: 186

Text #16

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0459. Min Act: -0.0001

Data Index: 1379000 (Python Code)

Max Activating Token Index: 374

Text #17

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0421. Min Act: -0.0001

Data Index: 1613171 (Python Code)

Max Activating Token Index: 131

Text #18

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0408. Min Act: -0.0001

Data Index: 1387518 (Python Code)

Max Activating Token Index: 1006

Text #19

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0415. Min Act: -0.0002

Data Index: 525432 (C4 (Web Text))

Max Activating Token Index: 334