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

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

Neuron 1028 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0658. Min Range: -1.0658

Max Act: 1.0658. Min Act: -0.0002

Data Index: 135663 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 1.0658. Min Range: -1.0658

Max Act: 1.0081. Min Act: -0.0001

Data Index: 456032 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 1.0658. Min Range: -1.0658

Max Act: 1.0111. Min Act: -0.0001

Data Index: 346459 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.9253. Min Act: -0.0002

Data Index: 1309847 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8354. Min Act: -0.0002

Data Index: 350606 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.9540. Min Act: -0.0002

Data Index: 1031843 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.9037. Min Act: -0.0001

Data Index: 113688 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8148. Min Act: -0.0002

Data Index: 1312589 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8725. Min Act: -0.0001

Data Index: 1173177 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8449. Min Act: -0.0001

Data Index: 17178 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8551. Min Act: -0.0002

Data Index: 559245 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8680. Min Act: -0.0002

Data Index: 518280 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8382. Min Act: -0.0001

Data Index: 1188379 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8393. Min Act: -0.0001

Data Index: 711363 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8523. Min Act: -0.0002

Data Index: 11134 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8848. Min Act: -0.0001

Data Index: 243534 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.7712. Min Act: -0.0001

Data Index: 1475082 (Python Code)

Max Activating Token Index: 977

Text #17

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8560. Min Act: -0.0001

Data Index: 1100159 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.7333. Min Act: -0.0002

Data Index: 767947 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8376. Min Act: -0.0002

Data Index: 653307 (C4 (Web Text))

Max Activating Token Index: 903