Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1976 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.5222. Min Act: -0.0000

Data Index: 46753 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.5384. Min Act: 0.0000

Data Index: 124343 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.5515. Min Act: -0.0000

Data Index: 428800 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.5297. Min Act: 0.0000

Data Index: 547805 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.5277. Min Act: 0.0000

Data Index: 612797 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.5155. Min Act: -0.0000

Data Index: 519817 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4787. Min Act: -0.0000

Data Index: 57490 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1058245 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4599. Min Act: 0.0001

Data Index: 924112 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4718. Min Act: -0.0000

Data Index: 831550 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4474. Min Act: -0.0000

Data Index: 870832 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4369. Min Act: -0.0000

Data Index: 101681 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4326. Min Act: -0.0000

Data Index: 684653 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4132. Min Act: -0.0000

Data Index: 167370 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4394. Min Act: -0.0000

Data Index: 973816 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4119. Min Act: -0.0000

Data Index: 1223620 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4071. Min Act: 0.0001

Data Index: 298809 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1186082 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3670. Min Act: 0.0000

Data Index: 1095178 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4084. Min Act: -0.0000

Data Index: 924830 (C4 (Web Text))

Max Activating Token Index: 612