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

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

Neuron 2600 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: 1.3037. Min Range: -1.3037

Max Act: 1.3037. Min Act: -0.0001

Data Index: 293718 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.2108. Min Act: -0.0002

Data Index: 526511 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.2356. Min Act: -0.0002

Data Index: 376636 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.1697. Min Act: -0.0001

Data Index: 483053 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.1267. Min Act: -0.0001

Data Index: 1072126 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.0518. Min Act: -0.0001

Data Index: 1134705 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.0654. Min Act: -0.0001

Data Index: 405812 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.0917. Min Act: -0.0001

Data Index: 90732 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.1140. Min Act: -0.0001

Data Index: 1162337 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.0751. Min Act: -0.0001

Data Index: 1201847 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.0121. Min Act: -0.0001

Data Index: 1225334 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.0213. Min Act: -0.0001

Data Index: 614439 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 1.3037. Min Range: -1.3037

Max Act: 0.9922. Min Act: -0.0001

Data Index: 1192058 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.0198. Min Act: -0.0001

Data Index: 515237 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 1.3037. Min Range: -1.3037

Max Act: 1.0333. Min Act: -0.0001

Data Index: 71513 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 1.3037. Min Range: -1.3037

Max Act: 0.9722. Min Act: -0.0001

Data Index: 1180890 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 1.3037. Min Range: -1.3037

Max Act: 0.9677. Min Act: -0.0001

Data Index: 409889 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 1.3037. Min Range: -1.3037

Max Act: 0.9701. Min Act: -0.0001

Data Index: 1220702 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 1.3037. Min Range: -1.3037

Max Act: 0.9653. Min Act: -0.0001

Data Index: 1166182 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 1.3037. Min Range: -1.3037

Max Act: 0.8973. Min Act: -0.0001

Data Index: 451751 (C4 (Web Text))

Max Activating Token Index: 446