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

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

Neuron 2792 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: 4.0182. Min Range: -4.0182

Max Act: 3.8393. Min Act: -0.0001

Data Index: 373158 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.9661. Min Act: -0.0001

Data Index: 1088091 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 4.0182. Min Range: -4.0182

Max Act: 4.0182. Min Act: -0.0000

Data Index: 466655 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.6978. Min Act: -0.0001

Data Index: 315305 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.8313. Min Act: -0.0000

Data Index: 1006802 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.8255. Min Act: -0.0001

Data Index: 847950 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.8161. Min Act: -0.0001

Data Index: 160908 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.6438. Min Act: -0.0001

Data Index: 189149 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.6657. Min Act: -0.0001

Data Index: 1046758 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.5158. Min Act: -0.0001

Data Index: 531900 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.5055. Min Act: -0.0001

Data Index: 197168 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.4769. Min Act: -0.0001

Data Index: 163459 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.2792. Min Act: -0.0001

Data Index: 747322 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.4279. Min Act: -0.0001

Data Index: 361613 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.4114. Min Act: -0.0001

Data Index: 1142184 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.3590. Min Act: -0.0001

Data Index: 880055 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.3067. Min Act: -0.0001

Data Index: 1289827 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.2742. Min Act: -0.0001

Data Index: 1190857 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.2363. Min Act: -0.0000

Data Index: 614532 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.2185. Min Act: -0.0001

Data Index: 456326 (C4 (Web Text))

Max Activating Token Index: 282