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

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

Neuron 1159 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.6769. Min Act: -0.0001

Data Index: 100908 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.6890. Min Act: -0.0002

Data Index: 266164 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.6502. Min Act: -0.0002

Data Index: 1267050 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.6365. Min Act: -0.0002

Data Index: 852173 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4770. Min Act: -0.0001

Data Index: 200682 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.6379. Min Act: -0.0001

Data Index: 105435 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.6358. Min Act: -0.0002

Data Index: 18495 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.6190. Min Act: -0.0001

Data Index: 303340 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.6039. Min Act: -0.0001

Data Index: 514869 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.6140. Min Act: -0.0002

Data Index: 244019 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5616. Min Act: -0.0001

Data Index: 713320 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5593. Min Act: -0.0002

Data Index: 177850 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5760. Min Act: -0.0001

Data Index: 1298283 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5717. Min Act: -0.0001

Data Index: 262062 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5697. Min Act: -0.0001

Data Index: 184971 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5580. Min Act: -0.0001

Data Index: 1011021 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5560. Min Act: -0.0001

Data Index: 483442 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.6429. Min Act: -0.0002

Data Index: 1032233 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5614. Min Act: -0.0002

Data Index: 180412 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5270. Min Act: -0.0002

Data Index: 149031 (C4 (Web Text))

Max Activating Token Index: 756