Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1778 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1203. Min Act: 0.0000

Data Index: 973038 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1103. Min Act: -0.0001

Data Index: 764138 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1103. Min Act: -0.0000

Data Index: 1231466 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1048. Min Act: -0.0000

Data Index: 613558 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1041. Min Act: -0.0000

Data Index: 1136914 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1016. Min Act: -0.0000

Data Index: 750312 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0943. Min Act: -0.0000

Data Index: 1036158 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0954. Min Act: -0.0000

Data Index: 932000 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0940. Min Act: -0.0000

Data Index: 723323 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0964. Min Act: -0.0000

Data Index: 894172 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0962. Min Act: -0.0000

Data Index: 148452 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0909. Min Act: -0.0000

Data Index: 602231 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1258064 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0877. Min Act: 0.0000

Data Index: 386448 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0921. Min Act: -0.0000

Data Index: 82627 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0890. Min Act: -0.0000

Data Index: 143251 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0916. Min Act: -0.0000

Data Index: 599114 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0934. Min Act: -0.0000

Data Index: 1256296 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0897. Min Act: 0.0000

Data Index: 880625 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0863. Min Act: -0.0001

Data Index: 493168 (C4 (Web Text))

Max Activating Token Index: 231