Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3027 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.8071. Min Act: -0.0000

Data Index: 206620 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.7198. Min Act: -0.0000

Data Index: 1165902 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.6487. Min Act: -0.0000

Data Index: 853322 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.6395. Min Act: -0.0000

Data Index: 900075 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.6444. Min Act: -0.0000

Data Index: 958137 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.6119. Min Act: -0.0000

Data Index: 1213801 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.5766. Min Act: -0.0000

Data Index: 1007834 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.5730. Min Act: -0.0000

Data Index: 148249 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.4114. Min Act: -0.0000

Data Index: 274688 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.5100. Min Act: -0.0000

Data Index: 626462 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.4947. Min Act: -0.0000

Data Index: 13226 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.1899. Min Act: -0.0000

Data Index: 766761 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.4044. Min Act: -0.0000

Data Index: 564395 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.3769. Min Act: -0.0000

Data Index: 951202 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.2332. Min Act: -0.0000

Data Index: 183247 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.2357. Min Act: -0.0000

Data Index: 286669 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.2172. Min Act: -0.0000

Data Index: 718739 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.2059. Min Act: -0.0000

Data Index: 1339057 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.1931. Min Act: -0.0000

Data Index: 456638 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.3059. Min Act: -0.0000

Data Index: 1056827 (C4 (Web Text))

Max Activating Token Index: 286