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

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

Neuron 697 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1150. Min Range: -1.1150

Max Act: 1.1150. Min Act: -0.0002

Data Index: 1294084 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 1.1150. Min Range: -1.1150

Max Act: 1.0859. Min Act: -0.0003

Data Index: 200400 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 1.1150. Min Range: -1.1150

Max Act: 1.0389. Min Act: -0.0002

Data Index: 266195 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 1.1150. Min Range: -1.1150

Max Act: 1.0630. Min Act: -0.0003

Data Index: 429218 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 1.1150. Min Range: -1.1150

Max Act: 1.0065. Min Act: -0.0003

Data Index: 1031565 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 1.1150. Min Range: -1.1150

Max Act: 0.9066. Min Act: -0.0003

Data Index: 459501 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 1.1150. Min Range: -1.1150

Max Act: 0.8803. Min Act: -0.0003

Data Index: 176156 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 1.1150. Min Range: -1.1150

Max Act: 0.8461. Min Act: -0.0003

Data Index: 899685 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 1.1150. Min Range: -1.1150

Max Act: 0.8933. Min Act: -0.0003

Data Index: 608072 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 1.1150. Min Range: -1.1150

Max Act: 0.8833. Min Act: -0.0003

Data Index: 1127941 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 1.1150. Min Range: -1.1150

Max Act: 0.8484. Min Act: -0.0003

Data Index: 332227 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 1.1150. Min Range: -1.1150

Max Act: 0.8773. Min Act: -0.0003

Data Index: 105222 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 1.1150. Min Range: -1.1150

Max Act: 0.8613. Min Act: -0.0002

Data Index: 1289802 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 1.1150. Min Range: -1.1150

Max Act: 0.8628. Min Act: -0.0002

Data Index: 749031 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 1.1150. Min Range: -1.1150

Max Act: 0.8595. Min Act: -0.0002

Data Index: 858972 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 1.1150. Min Range: -1.1150

Max Act: 0.8288. Min Act: -0.0002

Data Index: 495487 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 1.1150. Min Range: -1.1150

Max Act: 0.8242. Min Act: -0.0003

Data Index: 549216 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 1.1150. Min Range: -1.1150

Max Act: 0.8266. Min Act: -0.0002

Data Index: 539889 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 1.1150. Min Range: -1.1150

Max Act: 0.8426. Min Act: -0.0003

Data Index: 582663 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 1.1150. Min Range: -1.1150

Max Act: 0.8213. Min Act: -0.0003

Data Index: 598557 (C4 (Web Text))

Max Activating Token Index: 42