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

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

Neuron 2830 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1194. Min Act: -0.0001

Data Index: 1307529 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1206. Min Act: -0.0002

Data Index: 834111 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1019. Min Act: -0.0002

Data Index: 1201413 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1026. Min Act: -0.0002

Data Index: 665335 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0978. Min Act: -0.0002

Data Index: 19649 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0958. Min Act: -0.0002

Data Index: 505607 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0888. Min Act: -0.0002

Data Index: 77542 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0842. Min Act: -0.0001

Data Index: 326758 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0986. Min Act: -0.0001

Data Index: 404191 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0986. Min Act: -0.0002

Data Index: 1026707 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0912. Min Act: -0.0002

Data Index: 288079 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1652200 (Python Code)

Max Activating Token Index: 747

Text #12

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0970. Min Act: -0.0001

Data Index: 315961 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0904. Min Act: -0.0001

Data Index: 404280 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0880. Min Act: -0.0001

Data Index: 691963 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0917. Min Act: -0.0002

Data Index: 1191198 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0805. Min Act: -0.0001

Data Index: 305541 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0838. Min Act: -0.0001

Data Index: 859182 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1354925 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0868. Min Act: -0.0002

Data Index: 965855 (C4 (Web Text))

Max Activating Token Index: 907