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

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

Neuron 3683 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7660. Min Act: -0.0000

Data Index: 900638 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7115. Min Act: -0.0000

Data Index: 1027773 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5792. Min Act: -0.0000

Data Index: 87349 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5552. Min Act: -0.0000

Data Index: 384514 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5328. Min Act: -0.0000

Data Index: 718757 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1038951 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1226327 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.4866. Min Act: -0.0000

Data Index: 37600 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.4755. Min Act: -0.0000

Data Index: 1100566 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.4847. Min Act: -0.0000

Data Index: 323865 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.4403. Min Act: -0.0000

Data Index: 331009 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.4436. Min Act: -0.0000

Data Index: 259991 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.4475. Min Act: -0.0000

Data Index: 633010 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.4639. Min Act: -0.0000

Data Index: 971450 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.4236. Min Act: -0.0000

Data Index: 194118 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1046268 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.4086. Min Act: -0.0000

Data Index: 832977 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.4186. Min Act: -0.0000

Data Index: 886814 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.3994. Min Act: -0.0000

Data Index: 783789 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.4143. Min Act: -0.0000

Data Index: 331819 (C4 (Web Text))

Max Activating Token Index: 617