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

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

Neuron 5545 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.5201. Min Act: -0.0000

Data Index: 62788 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4875. Min Act: 0.0000

Data Index: 1030746 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4357. Min Act: -0.0000

Data Index: 321075 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4257. Min Act: -0.0000

Data Index: 406688 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1062434 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.4083. Min Act: -0.0000

Data Index: 525970 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3496. Min Act: -0.0000

Data Index: 129953 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3341. Min Act: -0.0000

Data Index: 684407 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3281. Min Act: -0.0000

Data Index: 762737 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1279410 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3296. Min Act: -0.0000

Data Index: 429079 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3166. Min Act: -0.0000

Data Index: 768493 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3066. Min Act: -0.0000

Data Index: 574661 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3145. Min Act: -0.0000

Data Index: 561967 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3115. Min Act: -0.0000

Data Index: 814129 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3017. Min Act: -0.0000

Data Index: 527855 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3097. Min Act: -0.0000

Data Index: 248354 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3093. Min Act: -0.0000

Data Index: 878052 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.2957. Min Act: -0.0000

Data Index: 1005157 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.5201. Min Range: -0.5201

Max Act: 0.3033. Min Act: 0.0000

Data Index: 213146 (C4 (Web Text))

Max Activating Token Index: 58