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

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

Neuron 2895 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: 0.6913. Min Range: -0.6913

Max Act: 0.6550. Min Act: -0.0000

Data Index: 528047 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6913. Min Act: -0.0000

Data Index: 124844 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6348. Min Act: -0.0000

Data Index: 524742 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.6293. Min Act: -0.0000

Data Index: 425762 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.5155. Min Act: -0.0001

Data Index: 33451 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1354205 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.5433. Min Act: -0.0000

Data Index: 758789 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.5524. Min Act: -0.0000

Data Index: 202155 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.5193. Min Act: -0.0000

Data Index: 496380 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.5246. Min Act: -0.0000

Data Index: 113425 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1140332 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.5983. Min Act: -0.0000

Data Index: 1268996 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1082243 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.4986. Min Act: -0.0000

Data Index: 330080 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.4553. Min Act: -0.0000

Data Index: 818717 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1219879 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.4850. Min Act: -0.0000

Data Index: 1178736 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.4963. Min Act: -0.0000

Data Index: 466136 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.4255. Min Act: -0.0000

Data Index: 693618 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.6913. Min Range: -0.6913

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1230856 (C4 (Web Text))

Max Activating Token Index: 630