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

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

Neuron 625 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: 1.7284. Min Range: -1.7284

Max Act: 1.7284. Min Act: -0.0000

Data Index: 782876 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 1.7284. Min Range: -1.7284

Max Act: 1.4831. Min Act: -0.0000

Data Index: 620879 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 1.7284. Min Range: -1.7284

Max Act: 1.2440. Min Act: -0.0001

Data Index: 1143520 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 1.7284. Min Range: -1.7284

Max Act: 1.2766. Min Act: -0.0001

Data Index: 208061 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 1.7284. Min Range: -1.7284

Max Act: 1.1968. Min Act: -0.0001

Data Index: 482316 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 1.7284. Min Range: -1.7284

Max Act: 1.2165. Min Act: -0.0001

Data Index: 367989 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 1.7284. Min Range: -1.7284

Max Act: 0.9930. Min Act: -0.0001

Data Index: 865880 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 1.7284. Min Range: -1.7284

Max Act: 0.9393. Min Act: -0.0001

Data Index: 457271 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 1.7284. Min Range: -1.7284

Max Act: 1.0558. Min Act: -0.0001

Data Index: 1094576 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 1.7284. Min Range: -1.7284

Max Act: 0.9117. Min Act: -0.0000

Data Index: 139074 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 1.7284. Min Range: -1.7284

Max Act: 0.9774. Min Act: -0.0001

Data Index: 941686 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 1.7284. Min Range: -1.7284

Max Act: 0.8234. Min Act: -0.0001

Data Index: 193950 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 1.7284. Min Range: -1.7284

Max Act: 0.8054. Min Act: -0.0001

Data Index: 618322 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 1.7284. Min Range: -1.7284

Max Act: 0.8231. Min Act: -0.0000

Data Index: 310834 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 1.7284. Min Range: -1.7284

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1353194 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.7284. Min Range: -1.7284

Max Act: 0.7716. Min Act: -0.0001

Data Index: 75082 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 1.7284. Min Range: -1.7284

Max Act: 0.7420. Min Act: -0.0001

Data Index: 494740 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 1.7284. Min Range: -1.7284

Max Act: 0.7528. Min Act: -0.0000

Data Index: 106806 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 1.7284. Min Range: -1.7284

Max Act: 0.7494. Min Act: -0.0001

Data Index: 865966 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 1.7284. Min Range: -1.7284

Max Act: 0.7322. Min Act: -0.0001

Data Index: 166479 (C4 (Web Text))

Max Activating Token Index: 281