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

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

Neuron 770 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3699. Min Act: -0.0002

Data Index: 775911 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3675. Min Act: -0.0002

Data Index: 814240 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3485. Min Act: -0.0002

Data Index: 3016 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3427. Min Act: -0.0002

Data Index: 809454 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3380. Min Act: -0.0002

Data Index: 373737 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3411. Min Act: -0.0002

Data Index: 640575 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3289. Min Act: -0.0002

Data Index: 23015 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3304. Min Act: -0.0002

Data Index: 421084 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3251. Min Act: -0.0002

Data Index: 1260973 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3235. Min Act: -0.0002

Data Index: 1332809 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3160. Min Act: -0.0002

Data Index: 237643 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3200. Min Act: -0.0002

Data Index: 919161 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3076. Min Act: -0.0002

Data Index: 1056376 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3077. Min Act: -0.0003

Data Index: 659179 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3087. Min Act: -0.0002

Data Index: 713507 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3090. Min Act: -0.0002

Data Index: 1252688 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3043. Min Act: -0.0002

Data Index: 304761 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3092. Min Act: -0.0002

Data Index: 1323838 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3033. Min Act: -0.0002

Data Index: 64653 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3069. Min Act: -0.0002

Data Index: 305755 (C4 (Web Text))

Max Activating Token Index: 266