Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2557 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.8263. Min Act: -0.0000

Data Index: 1251314 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.7357. Min Act: -0.0000

Data Index: 209237 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.5396. Min Act: -0.0000

Data Index: 986395 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.8076. Min Act: -0.0000

Data Index: 812437 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.6915. Min Act: -0.0000

Data Index: 404688 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.7484. Min Act: -0.0000

Data Index: 906102 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.6962. Min Act: -0.0000

Data Index: 131359 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.6986. Min Act: -0.0000

Data Index: 769532 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.4731. Min Act: -0.0000

Data Index: 1048577 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.5758. Min Act: -0.0000

Data Index: 44499 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.5062. Min Act: -0.0000

Data Index: 1317962 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.5100. Min Act: -0.0000

Data Index: 1170058 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.6913. Min Act: -0.0000

Data Index: 570965 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.5910. Min Act: -0.0000

Data Index: 132276 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.4946. Min Act: -0.0000

Data Index: 1013914 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.4944. Min Act: -0.0000

Data Index: 119944 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.5727. Min Act: -0.0000

Data Index: 187897 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.4022. Min Act: -0.0000

Data Index: 144697 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.4684. Min Act: -0.0000

Data Index: 878912 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 1.8263. Min Range: -1.8263

Max Act: 1.3514. Min Act: -0.0000

Data Index: 85269 (C4 (Web Text))

Max Activating Token Index: 518