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

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

Neuron 182 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.6038. Min Act: -0.0001

Data Index: 407536 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.6018. Min Act: -0.0001

Data Index: 836082 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.5708. Min Act: -0.0001

Data Index: 963744 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.5648. Min Act: -0.0001

Data Index: 1138003 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.4863. Min Act: -0.0001

Data Index: 928955 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.4849. Min Act: -0.0001

Data Index: 1285592 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.4612. Min Act: -0.0001

Data Index: 1308290 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.4759. Min Act: -0.0001

Data Index: 669601 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.4353. Min Act: -0.0001

Data Index: 1113533 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.4792. Min Act: -0.0001

Data Index: 1043203 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.4812. Min Act: -0.0001

Data Index: 791904 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.4664. Min Act: -0.0001

Data Index: 98054 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.4695. Min Act: -0.0001

Data Index: 41137 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1147827 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.4399. Min Act: -0.0001

Data Index: 617612 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.4319. Min Act: -0.0001

Data Index: 37329 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.4545. Min Act: -0.0001

Data Index: 214813 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.4504. Min Act: -0.0001

Data Index: 223679 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.4095. Min Act: -0.0001

Data Index: 386723 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.6038. Min Range: -0.6038

Max Act: 0.4320. Min Act: -0.0001

Data Index: 318196 (C4 (Web Text))

Max Activating Token Index: 693