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

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

Neuron 207 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: 4.5882. Min Range: -4.5882

Max Act: 4.5882. Min Act: -0.0001

Data Index: 825463 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 4.5882. Min Range: -4.5882

Max Act: 4.1723. Min Act: -0.0001

Data Index: 212214 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 4.5882. Min Range: -4.5882

Max Act: 3.7427. Min Act: -0.0001

Data Index: 700208 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 4.5882. Min Range: -4.5882

Max Act: 3.7323. Min Act: -0.0000

Data Index: 725436 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 4.5882. Min Range: -4.5882

Max Act: 3.6220. Min Act: -0.0001

Data Index: 1063300 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 4.5882. Min Range: -4.5882

Max Act: 3.3652. Min Act: -0.0001

Data Index: 496009 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 4.5882. Min Range: -4.5882

Max Act: 3.3741. Min Act: -0.0000

Data Index: 2558 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 4.5882. Min Range: -4.5882

Max Act: 3.6073. Min Act: -0.0001

Data Index: 1061253 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 4.5882. Min Range: -4.5882

Max Act: 3.6843. Min Act: -0.0001

Data Index: 558536 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 4.5882. Min Range: -4.5882

Max Act: 3.4658. Min Act: -0.0001

Data Index: 1219499 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 4.5882. Min Range: -4.5882

Max Act: 3.0647. Min Act: -0.0001

Data Index: 672162 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 4.5882. Min Range: -4.5882

Max Act: 3.4361. Min Act: -0.0001

Data Index: 518899 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 4.5882. Min Range: -4.5882

Max Act: 3.3197. Min Act: -0.0001

Data Index: 1164225 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 4.5882. Min Range: -4.5882

Max Act: 3.2783. Min Act: -0.0001

Data Index: 14492 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 4.5882. Min Range: -4.5882

Max Act: 3.0190. Min Act: -0.0000

Data Index: 744888 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 4.5882. Min Range: -4.5882

Max Act: 2.8790. Min Act: -0.0000

Data Index: 296627 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 4.5882. Min Range: -4.5882

Max Act: 3.1310. Min Act: -0.0001

Data Index: 531486 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 4.5882. Min Range: -4.5882

Max Act: 2.9940. Min Act: -0.0000

Data Index: 1149964 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 4.5882. Min Range: -4.5882

Max Act: 3.0986. Min Act: -0.0001

Data Index: 752264 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 4.5882. Min Range: -4.5882

Max Act: 2.9654. Min Act: -0.0001

Data Index: 1183947 (C4 (Web Text))

Max Activating Token Index: 266