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

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

Neuron 3793 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.3913. Min Act: -0.0000

Data Index: 544951 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.2129. Min Act: -0.0000

Data Index: 1075320 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.0860. Min Act: -0.0000

Data Index: 1066719 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.0456. Min Act: -0.0000

Data Index: 1107409 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.0427. Min Act: -0.0000

Data Index: 248981 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 1.3913. Min Range: -1.3913

Max Act: 0.9460. Min Act: -0.0000

Data Index: 1350918 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 1.3913. Min Range: -1.3913

Max Act: 1.0078. Min Act: -0.0000

Data Index: 283963 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 1.3913. Min Range: -1.3913

Max Act: 0.9654. Min Act: -0.0000

Data Index: 381406 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 1.3913. Min Range: -1.3913

Max Act: 0.8995. Min Act: -0.0000

Data Index: 527339 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 1.3913. Min Range: -1.3913

Max Act: 0.8972. Min Act: -0.0000

Data Index: 847651 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 1.3913. Min Range: -1.3913

Max Act: 0.9221. Min Act: -0.0000

Data Index: 275233 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 1.3913. Min Range: -1.3913

Max Act: 0.9008. Min Act: -0.0000

Data Index: 611002 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 1.3913. Min Range: -1.3913

Max Act: 0.9422. Min Act: -0.0000

Data Index: 223661 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 1.3913. Min Range: -1.3913

Max Act: 0.9146. Min Act: -0.0000

Data Index: 1345474 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 1.3913. Min Range: -1.3913

Max Act: 0.9382. Min Act: 0.0000

Data Index: 410465 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 1.3913. Min Range: -1.3913

Max Act: 0.9298. Min Act: -0.0000

Data Index: 898142 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 1.3913. Min Range: -1.3913

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1000499 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 1.3913. Min Range: -1.3913

Max Act: 0.9008. Min Act: -0.0000

Data Index: 1170658 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 1.3913. Min Range: -1.3913

Max Act: 0.9257. Min Act: -0.0000

Data Index: 812280 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 1.3913. Min Range: -1.3913

Max Act: 0.9308. Min Act: -0.0000

Data Index: 829159 (C4 (Web Text))

Max Activating Token Index: 381