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

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

Neuron 2768 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: 0.5580. Min Range: -0.5580

Max Act: 0.5580. Min Act: -0.0000

Data Index: 56556 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.5240. Min Act: -0.0000

Data Index: 96109 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4916. Min Act: -0.0000

Data Index: 337663 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4692. Min Act: -0.0000

Data Index: 955438 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4481. Min Act: -0.0000

Data Index: 581723 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4441. Min Act: -0.0000

Data Index: 165235 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1036748 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4490. Min Act: -0.0000

Data Index: 265596 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.5038. Min Act: -0.0001

Data Index: 803658 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4380. Min Act: -0.0000

Data Index: 428318 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4515. Min Act: -0.0001

Data Index: 1230134 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1229028 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4406. Min Act: -0.0001

Data Index: 861640 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4050. Min Act: -0.0000

Data Index: 370100 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4270. Min Act: -0.0001

Data Index: 534217 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1275425 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4502. Min Act: -0.0001

Data Index: 45886 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1353811 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1122163 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.5580. Min Range: -0.5580

Max Act: 0.4482. Min Act: -0.0001

Data Index: 690876 (C4 (Web Text))

Max Activating Token Index: 741