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

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

Neuron 3105 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.6351. Min Act: -0.0000

Data Index: 536346 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.6305. Min Act: -0.0000

Data Index: 307078 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5937. Min Act: -0.0000

Data Index: 775547 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5979. Min Act: -0.0000

Data Index: 793305 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5443. Min Act: -0.0000

Data Index: 70223 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5622. Min Act: -0.0001

Data Index: 812503 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5000. Min Act: -0.0001

Data Index: 468060 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5524. Min Act: -0.0001

Data Index: 337352 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5085. Min Act: -0.0000

Data Index: 560452 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4716. Min Act: -0.0000

Data Index: 850050 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4851. Min Act: -0.0001

Data Index: 1288678 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4842. Min Act: -0.0000

Data Index: 1244551 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4566. Min Act: -0.0000

Data Index: 237808 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4982. Min Act: -0.0001

Data Index: 179949 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4620. Min Act: -0.0000

Data Index: 138392 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4708. Min Act: -0.0000

Data Index: 198672 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4498. Min Act: -0.0001

Data Index: 998131 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4642. Min Act: -0.0000

Data Index: 777937 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4795. Min Act: -0.0000

Data Index: 463673 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4611. Min Act: -0.0000

Data Index: 1250012 (C4 (Web Text))

Max Activating Token Index: 403