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

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

Neuron 3870 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7839. Min Range: -2.7839

Max Act: 2.7839. Min Act: -0.0000

Data Index: 937497 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 2.7839. Min Range: -2.7839

Max Act: 1.7556. Min Act: -0.0000

Data Index: 1242940 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 2.7839. Min Range: -2.7839

Max Act: 1.8177. Min Act: -0.0000

Data Index: 548894 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 2.7839. Min Range: -2.7839

Max Act: 1.7081. Min Act: -0.0000

Data Index: 42240 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 2.7839. Min Range: -2.7839

Max Act: 1.6921. Min Act: -0.0000

Data Index: 539833 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 2.7839. Min Range: -2.7839

Max Act: 1.5711. Min Act: -0.0000

Data Index: 1353393 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 2.7839. Min Range: -2.7839

Max Act: 1.6488. Min Act: -0.0000

Data Index: 1236799 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 2.7839. Min Range: -2.7839

Max Act: 1.6517. Min Act: -0.0000

Data Index: 675276 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 2.7839. Min Range: -2.7839

Max Act: 1.6358. Min Act: -0.0000

Data Index: 157064 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 2.7839. Min Range: -2.7839

Max Act: 1.5481. Min Act: -0.0000

Data Index: 135490 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 2.7839. Min Range: -2.7839

Max Act: 1.7190. Min Act: -0.0000

Data Index: 987927 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 2.7839. Min Range: -2.7839

Max Act: 1.6166. Min Act: -0.0000

Data Index: 280414 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 2.7839. Min Range: -2.7839

Max Act: 1.5154. Min Act: -0.0000

Data Index: 478526 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 2.7839. Min Range: -2.7839

Max Act: 1.6009. Min Act: -0.0000

Data Index: 994926 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 2.7839. Min Range: -2.7839

Max Act: 1.5809. Min Act: -0.0000

Data Index: 1071831 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 2.7839. Min Range: -2.7839

Max Act: 1.5653. Min Act: -0.0000

Data Index: 1092245 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 2.7839. Min Range: -2.7839

Max Act: 1.5505. Min Act: -0.0000

Data Index: 143401 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 2.7839. Min Range: -2.7839

Max Act: 1.5378. Min Act: -0.0000

Data Index: 549605 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 2.7839. Min Range: -2.7839

Max Act: 1.2828. Min Act: -0.0000

Data Index: 370024 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 2.7839. Min Range: -2.7839

Max Act: 1.5005. Min Act: -0.0000

Data Index: 852996 (C4 (Web Text))

Max Activating Token Index: 95