Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 474 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.0705. Min Range: -3.0705

Max Act: 3.0705. Min Act: -0.0001

Data Index: 393796 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.8025. Min Act: -0.0001

Data Index: 185734 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.6268. Min Act: -0.0001

Data Index: 856967 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.2263. Min Act: -0.0001

Data Index: 1020532 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.5677. Min Act: -0.0001

Data Index: 1324955 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.6440. Min Act: -0.0001

Data Index: 531266 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.8647. Min Act: -0.0001

Data Index: 1125829 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.7413. Min Act: -0.0001

Data Index: 290685 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.5928. Min Act: -0.0001

Data Index: 447514 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.5743. Min Act: -0.0001

Data Index: 252891 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.4218. Min Act: -0.0001

Data Index: 92569 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.6769. Min Act: -0.0001

Data Index: 994799 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.3613. Min Act: -0.0001

Data Index: 256443 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.4820. Min Act: -0.0001

Data Index: 1228439 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.4838. Min Act: -0.0001

Data Index: 70940 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.4818. Min Act: -0.0001

Data Index: 840876 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.4644. Min Act: -0.0001

Data Index: 449269 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.4840. Min Act: -0.0001

Data Index: 449151 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.4694. Min Act: -0.0001

Data Index: 1320687 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.3493. Min Act: -0.0001

Data Index: 1268939 (C4 (Web Text))

Max Activating Token Index: 401