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

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

Neuron 3403 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: 1.1826. Min Range: -1.1826

Max Act: 1.1826. Min Act: -0.0001

Data Index: 31223 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 1.1826. Min Range: -1.1826

Max Act: 1.0368. Min Act: -0.0000

Data Index: 739107 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9870. Min Act: -0.0001

Data Index: 1351316 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9910. Min Act: -0.0000

Data Index: 1133557 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9591. Min Act: -0.0001

Data Index: 887702 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9476. Min Act: -0.0000

Data Index: 831281 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9996. Min Act: -0.0001

Data Index: 593459 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9432. Min Act: -0.0001

Data Index: 492612 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9438. Min Act: -0.0001

Data Index: 1037961 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9132. Min Act: -0.0001

Data Index: 350915 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9299. Min Act: -0.0001

Data Index: 1220161 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.8813. Min Act: -0.0001

Data Index: 85746 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.8947. Min Act: -0.0000

Data Index: 341483 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9190. Min Act: -0.0001

Data Index: 1145859 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1203530 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9069. Min Act: -0.0001

Data Index: 656105 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9331. Min Act: -0.0000

Data Index: 317256 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9299. Min Act: -0.0001

Data Index: 1297017 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.8692. Min Act: -0.0001

Data Index: 1182761 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9030. Min Act: -0.0001

Data Index: 1311144 (C4 (Web Text))

Max Activating Token Index: 316