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

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

Neuron 2514 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.6260. Min Act: -0.0001

Data Index: 1437227 (Python Code)

Max Activating Token Index: 858

Text #1

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5746. Min Act: -0.0001

Data Index: 1564489 (Python Code)

Max Activating Token Index: 499

Text #2

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.6012. Min Act: -0.0001

Data Index: 1582896 (Python Code)

Max Activating Token Index: 215

Text #3

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1375533 (Python Code)

Max Activating Token Index: 906

Text #4

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5110. Min Act: -0.0000

Data Index: 499179 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5537. Min Act: -0.0000

Data Index: 192494 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4780. Min Act: -0.0000

Data Index: 312105 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4959. Min Act: -0.0000

Data Index: 244012 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4701. Min Act: -0.0001

Data Index: 1410531 (Python Code)

Max Activating Token Index: 343

Text #9

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4751. Min Act: -0.0000

Data Index: 786187 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4857. Min Act: -0.0001

Data Index: 1111664 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4684. Min Act: -0.0000

Data Index: 683186 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4410. Min Act: -0.0001

Data Index: 1473672 (Python Code)

Max Activating Token Index: 121

Text #13

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4615. Min Act: -0.0000

Data Index: 970837 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4489. Min Act: -0.0000

Data Index: 758644 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4448. Min Act: -0.0000

Data Index: 831794 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4543. Min Act: -0.0000

Data Index: 598666 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4615. Min Act: -0.0000

Data Index: 61571 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4247. Min Act: -0.0000

Data Index: 77622 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4253. Min Act: -0.0000

Data Index: 306335 (C4 (Web Text))

Max Activating Token Index: 870