Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3615 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.6362. Min Act: -0.0001

Data Index: 1016224 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.6141. Min Act: -0.0001

Data Index: 942385 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5995. Min Act: -0.0000

Data Index: 297710 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5568. Min Act: -0.0001

Data Index: 232577 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4463. Min Act: -0.0001

Data Index: 185343 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4250. Min Act: -0.0000

Data Index: 1310913 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4990. Min Act: -0.0000

Data Index: 255228 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4902. Min Act: -0.0001

Data Index: 107902 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.3363. Min Act: -0.0001

Data Index: 1265156 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5894. Min Act: -0.0001

Data Index: 133148 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4527. Min Act: -0.0001

Data Index: 733389 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4512. Min Act: -0.0000

Data Index: 820736 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.3699. Min Act: -0.0001

Data Index: 337606 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.3701. Min Act: -0.0001

Data Index: 814836 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4981. Min Act: -0.0001

Data Index: 114903 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4843. Min Act: -0.0001

Data Index: 677689 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.3923. Min Act: -0.0001

Data Index: 1130147 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4839. Min Act: -0.0001

Data Index: 87303 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4749. Min Act: -0.0000

Data Index: 715565 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.1761. Min Act: -0.0001

Data Index: 1139946 (C4 (Web Text))

Max Activating Token Index: 709