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

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

Neuron 3000 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0761. Min Range: -2.0761

Max Act: 2.0761. Min Act: -0.0000

Data Index: 1007107 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 2.0761. Min Range: -2.0761

Max Act: 1.9321. Min Act: -0.0000

Data Index: 1024240 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 2.0761. Min Range: -2.0761

Max Act: 1.8407. Min Act: -0.0000

Data Index: 635653 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 2.0761. Min Range: -2.0761

Max Act: 1.8688. Min Act: -0.0000

Data Index: 573329 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 2.0761. Min Range: -2.0761

Max Act: 1.7609. Min Act: -0.0000

Data Index: 163436 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 2.0761. Min Range: -2.0761

Max Act: 1.8003. Min Act: -0.0000

Data Index: 812478 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 2.0761. Min Range: -2.0761

Max Act: 1.7147. Min Act: -0.0000

Data Index: 593923 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 2.0761. Min Range: -2.0761

Max Act: 1.6174. Min Act: -0.0000

Data Index: 783020 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 2.0761. Min Range: -2.0761

Max Act: 1.4382. Min Act: -0.0000

Data Index: 313887 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 2.0761. Min Range: -2.0761

Max Act: 1.5989. Min Act: -0.0000

Data Index: 714297 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 2.0761. Min Range: -2.0761

Max Act: 1.4049. Min Act: -0.0000

Data Index: 89492 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 2.0761. Min Range: -2.0761

Max Act: 1.5014. Min Act: -0.0000

Data Index: 196027 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 2.0761. Min Range: -2.0761

Max Act: 1.5704. Min Act: -0.0000

Data Index: 406452 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 2.0761. Min Range: -2.0761

Max Act: 1.6240. Min Act: -0.0000

Data Index: 798305 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 2.0761. Min Range: -2.0761

Max Act: 1.6854. Min Act: -0.0000

Data Index: 1127194 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 2.0761. Min Range: -2.0761

Max Act: 1.4404. Min Act: -0.0000

Data Index: 1302940 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 2.0761. Min Range: -2.0761

Max Act: 1.4285. Min Act: -0.0000

Data Index: 249244 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 2.0761. Min Range: -2.0761

Max Act: 1.4814. Min Act: -0.0000

Data Index: 839016 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 2.0761. Min Range: -2.0761

Max Act: 1.4318. Min Act: -0.0000

Data Index: 813098 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 2.0761. Min Range: -2.0761

Max Act: 1.4523. Min Act: -0.0000

Data Index: 67984 (C4 (Web Text))

Max Activating Token Index: 143