Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1199 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.7675. Min Act: -0.0001

Data Index: 1200527 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.8487. Min Act: -0.0001

Data Index: 411182 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.8008. Min Act: -0.0001

Data Index: 544807 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.7379. Min Act: -0.0001

Data Index: 263563 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.6592. Min Act: -0.0001

Data Index: 84825 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.6416. Min Act: -0.0001

Data Index: 243734 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.6149. Min Act: -0.0001

Data Index: 1127249 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.5609. Min Act: -0.0001

Data Index: 446124 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.6033. Min Act: -0.0001

Data Index: 513025 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.6554. Min Act: -0.0001

Data Index: 927861 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.5513. Min Act: -0.0001

Data Index: 812370 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.5865. Min Act: -0.0001

Data Index: 854545 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.5534. Min Act: -0.0001

Data Index: 514252 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.5377. Min Act: -0.0001

Data Index: 1023168 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.5661. Min Act: -0.0001

Data Index: 1071015 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.4945. Min Act: -0.0001

Data Index: 1063807 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.5882. Min Act: -0.0001

Data Index: 127061 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.5393. Min Act: -0.0001

Data Index: 1010707 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.5361. Min Act: -0.0001

Data Index: 41143 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 1.8487. Min Range: -1.8487

Max Act: 1.5303. Min Act: -0.0001

Data Index: 656450 (C4 (Web Text))

Max Activating Token Index: 912