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

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

Neuron 3413 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: 1.1271. Min Range: -1.1271

Max Act: 1.1271. Min Act: -0.0001

Data Index: 736324 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 1.1271. Min Range: -1.1271

Max Act: 1.0468. Min Act: -0.0001

Data Index: 861084 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 1.1271. Min Range: -1.1271

Max Act: 1.0193. Min Act: -0.0001

Data Index: 247931 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.9863. Min Act: -0.0002

Data Index: 210583 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 1.1271. Min Range: -1.1271

Max Act: 1.0742. Min Act: -0.0002

Data Index: 1275269 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.9591. Min Act: -0.0002

Data Index: 845945 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 1.1271. Min Range: -1.1271

Max Act: 1.0194. Min Act: -0.0001

Data Index: 123248 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8880. Min Act: -0.0002

Data Index: 1304513 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.9785. Min Act: -0.0002

Data Index: 1178857 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.9139. Min Act: -0.0002

Data Index: 482850 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8875. Min Act: -0.0001

Data Index: 435503 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.9371. Min Act: -0.0001

Data Index: 1018078 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.9406. Min Act: -0.0001

Data Index: 410209 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.9305. Min Act: -0.0001

Data Index: 1199716 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8858. Min Act: -0.0002

Data Index: 622262 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8809. Min Act: -0.0001

Data Index: 1298491 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.9293. Min Act: -0.0001

Data Index: 1253052 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.9756. Min Act: -0.0002

Data Index: 309429 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.9446. Min Act: -0.0002

Data Index: 1333373 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.9332. Min Act: -0.0002

Data Index: 759946 (C4 (Web Text))

Max Activating Token Index: 668