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

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

Neuron 3110 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3515. Min Range: -5.3515

Max Act: 5.3515. Min Act: -0.0000

Data Index: 67681 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 5.3515. Min Range: -5.3515

Max Act: 4.0273. Min Act: -0.0000

Data Index: 501227 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 5.3515. Min Range: -5.3515

Max Act: 4.3594. Min Act: -0.0000

Data Index: 563234 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 5.3515. Min Range: -5.3515

Max Act: 4.0554. Min Act: -0.0000

Data Index: 302119 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 5.3515. Min Range: -5.3515

Max Act: 4.2402. Min Act: -0.0000

Data Index: 1226810 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 5.3515. Min Range: -5.3515

Max Act: 4.2259. Min Act: -0.0000

Data Index: 245166 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 5.3515. Min Range: -5.3515

Max Act: 3.8635. Min Act: -0.0000

Data Index: 490542 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 5.3515. Min Range: -5.3515

Max Act: 3.7345. Min Act: -0.0000

Data Index: 1169788 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 5.3515. Min Range: -5.3515

Max Act: 3.4085. Min Act: -0.0000

Data Index: 143320 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 5.3515. Min Range: -5.3515

Max Act: 3.1441. Min Act: -0.0000

Data Index: 1242919 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 5.3515. Min Range: -5.3515

Max Act: 3.4509. Min Act: -0.0000

Data Index: 779531 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 5.3515. Min Range: -5.3515

Max Act: 3.7646. Min Act: -0.0000

Data Index: 1120338 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 5.3515. Min Range: -5.3515

Max Act: 3.3671. Min Act: -0.0000

Data Index: 991750 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 5.3515. Min Range: -5.3515

Max Act: 3.4382. Min Act: -0.0000

Data Index: 1046900 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 5.3515. Min Range: -5.3515

Max Act: 3.5243. Min Act: -0.0000

Data Index: 1033321 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 5.3515. Min Range: -5.3515

Max Act: 3.4853. Min Act: -0.0000

Data Index: 304468 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 5.3515. Min Range: -5.3515

Max Act: 3.4283. Min Act: -0.0000

Data Index: 624320 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 5.3515. Min Range: -5.3515

Max Act: 3.2070. Min Act: -0.0000

Data Index: 922518 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 5.3515. Min Range: -5.3515

Max Act: 3.2156. Min Act: -0.0000

Data Index: 1031347 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 5.3515. Min Range: -5.3515

Max Act: 3.1844. Min Act: -0.0000

Data Index: 355789 (C4 (Web Text))

Max Activating Token Index: 153