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

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

Neuron 899 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0495. Min Act: -0.0005

Data Index: 1164419 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0508. Min Act: -0.0005

Data Index: 1084430 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0483. Min Act: -0.0005

Data Index: 139504 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0466. Min Act: -0.0005

Data Index: 970186 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0456. Min Act: -0.0005

Data Index: 130087 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0440. Min Act: -0.0005

Data Index: 326762 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0452. Min Act: -0.0005

Data Index: 275143 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0481. Min Act: -0.0005

Data Index: 1200411 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0451. Min Act: -0.0005

Data Index: 681960 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0428. Min Act: -0.0005

Data Index: 187157 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0434. Min Act: -0.0005

Data Index: 945809 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0421. Min Act: -0.0005

Data Index: 425835 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0429. Min Act: -0.0005

Data Index: 1154542 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0438. Min Act: -0.0005

Data Index: 318726 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0430. Min Act: -0.0005

Data Index: 1181972 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0393. Min Act: -0.0005

Data Index: 459994 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0406. Min Act: -0.0005

Data Index: 507591 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0435. Min Act: -0.0005

Data Index: 1203935 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0412. Min Act: -0.0005

Data Index: 717483 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0388. Min Act: -0.0005

Data Index: 131524 (C4 (Web Text))

Max Activating Token Index: 345