Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1540 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.5857. Min Act: -0.0006

Data Index: 1388406 (Python Code)

Max Activating Token Index: 852

Text #1

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.2975. Min Act: -0.0006

Data Index: 1382997 (Python Code)

Max Activating Token Index: 970

Text #2

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.2750. Min Act: -0.0006

Data Index: 1643548 (Python Code)

Max Activating Token Index: 941

Text #3

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.2302. Min Act: -0.0006

Data Index: 1360693 (Python Code)

Max Activating Token Index: 866

Text #4

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.1718. Min Act: -0.0006

Data Index: 1422976 (Python Code)

Max Activating Token Index: 849

Text #5

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.1457. Min Act: -0.0006

Data Index: 1492056 (Python Code)

Max Activating Token Index: 977

Text #6

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.0901. Min Act: -0.0006

Data Index: 1612346 (Python Code)

Max Activating Token Index: 899

Text #7

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.0918. Min Act: -0.0006

Data Index: 1368412 (Python Code)

Max Activating Token Index: 967

Text #8

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.0674. Min Act: -0.0006

Data Index: 1598623 (Python Code)

Max Activating Token Index: 822

Text #9

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.0578. Min Act: -0.0006

Data Index: 1541186 (Python Code)

Max Activating Token Index: 938

Text #10

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.0512. Min Act: -0.0005

Data Index: 1587603 (Python Code)

Max Activating Token Index: 306

Text #11

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.0354. Min Act: -0.0006

Data Index: 368875 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.0373. Min Act: -0.0006

Data Index: 1423838 (Python Code)

Max Activating Token Index: 963

Text #13

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.0331. Min Act: -0.0006

Data Index: 827267 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.0352. Min Act: -0.0006

Data Index: 1575383 (Python Code)

Max Activating Token Index: 858

Text #15

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.0246. Min Act: -0.0006

Data Index: 1435770 (Python Code)

Max Activating Token Index: 469

Text #16

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.0373. Min Act: -0.0006

Data Index: 1582188 (Python Code)

Max Activating Token Index: 1020

Text #17

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.0303. Min Act: -0.0006

Data Index: 1629412 (Python Code)

Max Activating Token Index: 508

Text #18

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.0268. Min Act: -0.0006

Data Index: 1606495 (Python Code)

Max Activating Token Index: 359

Text #19

Max Range: 0.5857. Min Range: -0.5857

Max Act: 0.0300. Min Act: -0.0006

Data Index: 1519004 (Python Code)

Max Activating Token Index: 862