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

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

Neuron 1765 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: 4.2500. Min Range: -4.2500

Max Act: 4.1237. Min Act: -0.0001

Data Index: 1291598 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 4.2500. Min Range: -4.2500

Max Act: 4.2500. Min Act: -0.0000

Data Index: 1293483 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 4.2500. Min Range: -4.2500

Max Act: 3.3906. Min Act: -0.0001

Data Index: 756230 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 4.2500. Min Range: -4.2500

Max Act: 3.3261. Min Act: -0.0001

Data Index: 1263638 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 4.2500. Min Range: -4.2500

Max Act: 2.8541. Min Act: -0.0001

Data Index: 403589 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 4.2500. Min Range: -4.2500

Max Act: 2.8211. Min Act: -0.0000

Data Index: 720139 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 4.2500. Min Range: -4.2500

Max Act: 2.5730. Min Act: -0.0000

Data Index: 1068735 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 4.2500. Min Range: -4.2500

Max Act: 2.6642. Min Act: -0.0001

Data Index: 805725 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 4.2500. Min Range: -4.2500

Max Act: 3.0091. Min Act: -0.0000

Data Index: 146964 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 4.2500. Min Range: -4.2500

Max Act: 2.5795. Min Act: -0.0000

Data Index: 274323 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 4.2500. Min Range: -4.2500

Max Act: 2.4354. Min Act: -0.0000

Data Index: 229078 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 4.2500. Min Range: -4.2500

Max Act: 2.3916. Min Act: -0.0000

Data Index: 1122400 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 4.2500. Min Range: -4.2500

Max Act: 2.5249. Min Act: -0.0000

Data Index: 8937 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 4.2500. Min Range: -4.2500

Max Act: 2.5339. Min Act: -0.0001

Data Index: 726325 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 4.2500. Min Range: -4.2500

Max Act: 2.3244. Min Act: -0.0001

Data Index: 160932 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 4.2500. Min Range: -4.2500

Max Act: 2.3348. Min Act: -0.0001

Data Index: 826484 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 4.2500. Min Range: -4.2500

Max Act: 2.6841. Min Act: -0.0001

Data Index: 1059862 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 4.2500. Min Range: -4.2500

Max Act: 2.1874. Min Act: -0.0001

Data Index: 415473 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 4.2500. Min Range: -4.2500

Max Act: 2.3047. Min Act: -0.0000

Data Index: 1183715 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 4.2500. Min Range: -4.2500

Max Act: 2.3901. Min Act: -0.0000

Data Index: 354265 (C4 (Web Text))

Max Activating Token Index: 787