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

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

Neuron 2687 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: 2.5591. Min Range: -2.5591

Max Act: 2.5591. Min Act: -0.0000

Data Index: 875114 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.3527. Min Act: -0.0000

Data Index: 1334199 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.4244. Min Act: -0.0000

Data Index: 977175 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.4254. Min Act: -0.0000

Data Index: 405096 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.3862. Min Act: -0.0000

Data Index: 1285911 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.3640. Min Act: -0.0000

Data Index: 1205634 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.1865. Min Act: -0.0000

Data Index: 485163 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.3251. Min Act: -0.0000

Data Index: 377616 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.4213. Min Act: -0.0000

Data Index: 784003 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.2827. Min Act: -0.0000

Data Index: 933991 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.3891. Min Act: -0.0000

Data Index: 875707 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.1286. Min Act: -0.0000

Data Index: 762517 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.1877. Min Act: -0.0001

Data Index: 29452 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.1167. Min Act: -0.0000

Data Index: 549245 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.0198. Min Act: -0.0000

Data Index: 637538 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.2069. Min Act: -0.0000

Data Index: 825442 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 2.5591. Min Range: -2.5591

Max Act: 1.9610. Min Act: -0.0000

Data Index: 522847 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.1066. Min Act: -0.0000

Data Index: 119680 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.0836. Min Act: -0.0000

Data Index: 918481 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 2.5591. Min Range: -2.5591

Max Act: 2.1769. Min Act: -0.0000

Data Index: 649239 (C4 (Web Text))

Max Activating Token Index: 947