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

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

Neuron 1061 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8448. Min Range: -3.8448

Max Act: 3.8448. Min Act: -0.0000

Data Index: 1263128 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 3.8448. Min Range: -3.8448

Max Act: 3.4378. Min Act: -0.0000

Data Index: 888226 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 3.8448. Min Range: -3.8448

Max Act: 2.9978. Min Act: -0.0000

Data Index: 813179 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 3.8448. Min Range: -3.8448

Max Act: 3.2371. Min Act: -0.0000

Data Index: 521709 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 3.8448. Min Range: -3.8448

Max Act: 3.5259. Min Act: -0.0000

Data Index: 36540 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 3.8448. Min Range: -3.8448

Max Act: 3.4617. Min Act: -0.0000

Data Index: 201264 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 3.8448. Min Range: -3.8448

Max Act: 3.3115. Min Act: -0.0000

Data Index: 119081 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 3.8448. Min Range: -3.8448

Max Act: 3.3188. Min Act: -0.0000

Data Index: 859712 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 3.8448. Min Range: -3.8448

Max Act: 2.9887. Min Act: -0.0000

Data Index: 495201 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 3.8448. Min Range: -3.8448

Max Act: 3.0674. Min Act: -0.0000

Data Index: 1210592 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 3.8448. Min Range: -3.8448

Max Act: 2.8474. Min Act: -0.0000

Data Index: 177754 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 3.8448. Min Range: -3.8448

Max Act: 2.9559. Min Act: -0.0000

Data Index: 755797 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 3.8448. Min Range: -3.8448

Max Act: 2.6864. Min Act: -0.0000

Data Index: 566415 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 3.8448. Min Range: -3.8448

Max Act: 2.8202. Min Act: -0.0000

Data Index: 1063325 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 3.8448. Min Range: -3.8448

Max Act: 2.7858. Min Act: -0.0000

Data Index: 812662 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 3.8448. Min Range: -3.8448

Max Act: 2.6204. Min Act: -0.0000

Data Index: 762067 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 3.8448. Min Range: -3.8448

Max Act: 3.0372. Min Act: -0.0000

Data Index: 1212192 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 3.8448. Min Range: -3.8448

Max Act: 2.8465. Min Act: -0.0000

Data Index: 25860 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 3.8448. Min Range: -3.8448

Max Act: 2.8255. Min Act: -0.0000

Data Index: 658248 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 3.8448. Min Range: -3.8448

Max Act: 2.5497. Min Act: -0.0000

Data Index: 1073232 (C4 (Web Text))

Max Activating Token Index: 964