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

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

Neuron 907 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.4321. Min Act: -0.0002

Data Index: 859249 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.3777. Min Act: -0.0002

Data Index: 668432 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.3650. Min Act: -0.0002

Data Index: 147328 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.3508. Min Act: -0.0002

Data Index: 1139092 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.3606. Min Act: -0.0002

Data Index: 1259401 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.3704. Min Act: -0.0002

Data Index: 305630 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.3817. Min Act: -0.0002

Data Index: 460293 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.3707. Min Act: -0.0002

Data Index: 686004 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.3501. Min Act: -0.0002

Data Index: 1568131 (Python Code)

Max Activating Token Index: 59

Text #9

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.3393. Min Act: -0.0002

Data Index: 1607602 (Python Code)

Max Activating Token Index: 498

Text #10

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.3182. Min Act: -0.0002

Data Index: 269110 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.3401. Min Act: -0.0002

Data Index: 1214700 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.3594. Min Act: -0.0002

Data Index: 576173 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.3720. Min Act: -0.0002

Data Index: 25130 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.3263. Min Act: -0.0002

Data Index: 419064 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.3164. Min Act: -0.0002

Data Index: 793808 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.3316. Min Act: -0.0002

Data Index: 1335667 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.3392. Min Act: -0.0002

Data Index: 464031 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.2973. Min Act: -0.0002

Data Index: 946692 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.3354. Min Act: -0.0002

Data Index: 1607262 (Python Code)

Max Activating Token Index: 756