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

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

Neuron 5152 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: 2.8503. Min Range: -2.8503

Max Act: 2.8503. Min Act: -0.0000

Data Index: 44870 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 2.8503. Min Range: -2.8503

Max Act: 2.0991. Min Act: -0.0000

Data Index: 762985 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 2.8503. Min Range: -2.8503

Max Act: 1.7947. Min Act: -0.0000

Data Index: 53918 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 2.8503. Min Range: -2.8503

Max Act: 1.8638. Min Act: -0.0000

Data Index: 563274 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 2.8503. Min Range: -2.8503

Max Act: 1.8578. Min Act: -0.0000

Data Index: 1350216 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 2.8503. Min Range: -2.8503

Max Act: 1.8011. Min Act: -0.0000

Data Index: 727534 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 2.8503. Min Range: -2.8503

Max Act: 1.5737. Min Act: -0.0000

Data Index: 701382 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 2.8503. Min Range: -2.8503

Max Act: 1.5539. Min Act: -0.0000

Data Index: 85809 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 2.8503. Min Range: -2.8503

Max Act: 1.5322. Min Act: -0.0000

Data Index: 1131774 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 2.8503. Min Range: -2.8503

Max Act: 1.4760. Min Act: -0.0000

Data Index: 213629 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 2.8503. Min Range: -2.8503

Max Act: 1.4449. Min Act: -0.0000

Data Index: 100850 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 2.8503. Min Range: -2.8503

Max Act: 1.3765. Min Act: -0.0000

Data Index: 484404 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 2.8503. Min Range: -2.8503

Max Act: 1.3881. Min Act: -0.0000

Data Index: 536395 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 2.8503. Min Range: -2.8503

Max Act: 1.3550. Min Act: -0.0000

Data Index: 500715 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 2.8503. Min Range: -2.8503

Max Act: 1.3238. Min Act: -0.0000

Data Index: 1118983 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 2.8503. Min Range: -2.8503

Max Act: 1.2893. Min Act: -0.0000

Data Index: 879792 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 2.8503. Min Range: -2.8503

Max Act: 1.2931. Min Act: -0.0000

Data Index: 1297865 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 2.8503. Min Range: -2.8503

Max Act: 1.2859. Min Act: -0.0000

Data Index: 682729 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 2.8503. Min Range: -2.8503

Max Act: 1.2054. Min Act: -0.0000

Data Index: 1114183 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 2.8503. Min Range: -2.8503

Max Act: 1.2757. Min Act: -0.0000

Data Index: 1212514 (C4 (Web Text))

Max Activating Token Index: 52