Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 211 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.9918. Min Act: -0.0000

Data Index: 1206820 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.9606. Min Act: -0.0000

Data Index: 126837 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.9103. Min Act: -0.0000

Data Index: 899920 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1429593 (Python Code)

Max Activating Token Index: 194

Text #4

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.7943. Min Act: -0.0001

Data Index: 1416481 (Python Code)

Max Activating Token Index: 395

Text #5

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1252997 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.7781. Min Act: -0.0000

Data Index: 274070 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.7711. Min Act: -0.0000

Data Index: 544762 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1451100 (Python Code)

Max Activating Token Index: 493

Text #9

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.7538. Min Act: -0.0000

Data Index: 1336540 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.7436. Min Act: -0.0000

Data Index: 1244540 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1079934 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.7128. Min Act: -0.0001

Data Index: 799664 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.7334. Min Act: -0.0000

Data Index: 227566 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.7494. Min Act: -0.0000

Data Index: 698802 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.7290. Min Act: -0.0000

Data Index: 648159 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.7038. Min Act: -0.0000

Data Index: 193859 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1476819 (Python Code)

Max Activating Token Index: 107

Text #18

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.6867. Min Act: -0.0000

Data Index: 645654 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.6832. Min Act: -0.0000

Data Index: 1171449 (C4 (Web Text))

Max Activating Token Index: 141