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

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

Neuron 1366 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: 1.9497. Min Range: -1.9497

Max Act: 1.9294. Min Act: -0.0001

Data Index: 685928 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.8850. Min Act: -0.0002

Data Index: 1136811 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.4353. Min Act: -0.0002

Data Index: 372235 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.7280. Min Act: -0.0002

Data Index: 1197586 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.8792. Min Act: -0.0002

Data Index: 222091 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.5945. Min Act: -0.0001

Data Index: 160940 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.8910. Min Act: -0.0002

Data Index: 174864 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.6137. Min Act: -0.0002

Data Index: 985665 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.6351. Min Act: -0.0001

Data Index: 970855 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.9123. Min Act: -0.0002

Data Index: 343038 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.5456. Min Act: -0.0002

Data Index: 925832 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.5890. Min Act: -0.0001

Data Index: 1268989 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.9497. Min Act: -0.0001

Data Index: 472253 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.8644. Min Act: -0.0001

Data Index: 163481 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.5758. Min Act: -0.0001

Data Index: 174452 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.7143. Min Act: -0.0002

Data Index: 930227 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.6067. Min Act: -0.0001

Data Index: 1071707 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.7795. Min Act: -0.0002

Data Index: 1045873 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.8762. Min Act: -0.0002

Data Index: 1101916 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 1.9497. Min Range: -1.9497

Max Act: 1.8150. Min Act: -0.0002

Data Index: 974781 (C4 (Web Text))

Max Activating Token Index: 868