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

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

Neuron 3602 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.6022. Min Act: -0.0001

Data Index: 159429 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.3869. Min Act: -0.0001

Data Index: 937065 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.3332. Min Act: -0.0001

Data Index: 433796 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.2139. Min Act: -0.0001

Data Index: 851502 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.2638. Min Act: -0.0001

Data Index: 704775 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.1564. Min Act: -0.0001

Data Index: 85523 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.1130. Min Act: -0.0001

Data Index: 1179269 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.0340. Min Act: -0.0001

Data Index: 728016 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.0613. Min Act: -0.0001

Data Index: 215368 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.0473. Min Act: -0.0001

Data Index: 1505933 (Python Code)

Max Activating Token Index: 115

Text #10

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.0423. Min Act: -0.0001

Data Index: 429403 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.0802. Min Act: -0.0001

Data Index: 1421918 (Python Code)

Max Activating Token Index: 98

Text #12

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.0512. Min Act: -0.0001

Data Index: 1220903 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.0637. Min Act: -0.0001

Data Index: 1205974 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.0025. Min Act: -0.0001

Data Index: 1530040 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 1.6022. Min Range: -1.6022

Max Act: 0.9303. Min Act: -0.0001

Data Index: 959237 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.0021. Min Act: -0.0001

Data Index: 1518441 (Python Code)

Max Activating Token Index: 18

Text #17

Max Range: 1.6022. Min Range: -1.6022

Max Act: 0.9733. Min Act: -0.0001

Data Index: 1637883 (Python Code)

Max Activating Token Index: 71

Text #18

Max Range: 1.6022. Min Range: -1.6022

Max Act: 1.1170. Min Act: -0.0001

Data Index: 693359 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 1.6022. Min Range: -1.6022

Max Act: 0.9830. Min Act: -0.0001

Data Index: 341740 (C4 (Web Text))

Max Activating Token Index: 23