Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 281 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.6153. Min Act: -0.0003

Data Index: 237723 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.5343. Min Act: -0.0003

Data Index: 1278491 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4844. Min Act: -0.0003

Data Index: 1277906 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4625. Min Act: -0.0003

Data Index: 1065854 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4963. Min Act: -0.0003

Data Index: 1029602 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4748. Min Act: -0.0003

Data Index: 996990 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4781. Min Act: -0.0003

Data Index: 236296 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4613. Min Act: -0.0003

Data Index: 5339 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4240. Min Act: -0.0003

Data Index: 687547 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4321. Min Act: -0.0003

Data Index: 428500 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4429. Min Act: -0.0003

Data Index: 82989 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4413. Min Act: -0.0003

Data Index: 923023 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4067. Min Act: -0.0003

Data Index: 44557 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4053. Min Act: -0.0003

Data Index: 1319735 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4077. Min Act: -0.0003

Data Index: 801118 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.4080. Min Act: -0.0003

Data Index: 651320 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.3764. Min Act: -0.0003

Data Index: 317275 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.3815. Min Act: -0.0003

Data Index: 1288062 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.3631. Min Act: -0.0003

Data Index: 563454 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.6153. Min Range: -0.6153

Max Act: 0.3629. Min Act: -0.0003

Data Index: 244028 (C4 (Web Text))

Max Activating Token Index: 244