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

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

Neuron 4808 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.6791. Min Act: -0.0000

Data Index: 912710 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.6514. Min Act: -0.0000

Data Index: 330089 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.6276. Min Act: -0.0000

Data Index: 408431 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.6206. Min Act: -0.0000

Data Index: 748032 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.6129. Min Act: -0.0000

Data Index: 560689 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.5951. Min Act: -0.0000

Data Index: 239941 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1344549 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.6386. Min Act: -0.0000

Data Index: 387432 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.5986. Min Act: -0.0000

Data Index: 85203 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.5666. Min Act: -0.0000

Data Index: 36999 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.5629. Min Act: -0.0000

Data Index: 163897 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1153238 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.5330. Min Act: -0.0000

Data Index: 350647 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.5424. Min Act: -0.0000

Data Index: 828989 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.5386. Min Act: -0.0000

Data Index: 502469 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.5351. Min Act: -0.0000

Data Index: 76405 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.5233. Min Act: -0.0000

Data Index: 692609 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.5626. Min Act: -0.0000

Data Index: 567800 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.4894. Min Act: -0.0000

Data Index: 797193 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 0.6791. Min Range: -0.6791

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1168708 (C4 (Web Text))

Max Activating Token Index: 979