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

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

Neuron 4467 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: 2.2356. Min Range: -2.2356

Max Act: 2.2279. Min Act: -0.0000

Data Index: 897951 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 2.2356. Min Range: -2.2356

Max Act: 2.2356. Min Act: -0.0000

Data Index: 480181 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 2.2356. Min Range: -2.2356

Max Act: 2.1381. Min Act: -0.0000

Data Index: 1139424 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 2.2356. Min Range: -2.2356

Max Act: 2.0917. Min Act: -0.0000

Data Index: 1356242 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 2.2356. Min Range: -2.2356

Max Act: 2.0978. Min Act: -0.0000

Data Index: 661024 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 2.2356. Min Range: -2.2356

Max Act: 2.0724. Min Act: -0.0000

Data Index: 112115 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 2.2356. Min Range: -2.2356

Max Act: 2.1763. Min Act: -0.0000

Data Index: 1135102 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 2.2356. Min Range: -2.2356

Max Act: 2.0448. Min Act: -0.0000

Data Index: 157408 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 2.2356. Min Range: -2.2356

Max Act: 2.0504. Min Act: -0.0000

Data Index: 684930 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 2.2356. Min Range: -2.2356

Max Act: 2.0947. Min Act: -0.0000

Data Index: 872751 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 2.2356. Min Range: -2.2356

Max Act: 1.9717. Min Act: -0.0000

Data Index: 747308 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 2.2356. Min Range: -2.2356

Max Act: 2.0943. Min Act: -0.0000

Data Index: 631417 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 2.2356. Min Range: -2.2356

Max Act: 1.8555. Min Act: -0.0000

Data Index: 551542 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 2.2356. Min Range: -2.2356

Max Act: 2.0552. Min Act: -0.0000

Data Index: 909016 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 2.2356. Min Range: -2.2356

Max Act: 1.9307. Min Act: -0.0000

Data Index: 731904 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 2.2356. Min Range: -2.2356

Max Act: 2.0143. Min Act: -0.0000

Data Index: 1254086 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 2.2356. Min Range: -2.2356

Max Act: 1.7972. Min Act: -0.0000

Data Index: 158690 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 2.2356. Min Range: -2.2356

Max Act: 1.9083. Min Act: -0.0000

Data Index: 1057110 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 2.2356. Min Range: -2.2356

Max Act: 2.0019. Min Act: -0.0000

Data Index: 46119 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 2.2356. Min Range: -2.2356

Max Act: 1.8730. Min Act: -0.0000

Data Index: 1132907 (C4 (Web Text))

Max Activating Token Index: 936