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

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

Neuron 276 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1545. Min Act: -0.0000

Data Index: 993811 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1428854 (Python Code)

Max Activating Token Index: 10

Text #2

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1421. Min Act: -0.0000

Data Index: 172744 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1304. Min Act: -0.0000

Data Index: 394950 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1251. Min Act: -0.0000

Data Index: 57606 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1068. Min Act: -0.0000

Data Index: 767638 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1136. Min Act: -0.0000

Data Index: 503759 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1171. Min Act: -0.0001

Data Index: 1574369 (Python Code)

Max Activating Token Index: 502

Text #8

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1163. Min Act: -0.0000

Data Index: 698800 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1161. Min Act: -0.0000

Data Index: 1427846 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1200. Min Act: -0.0000

Data Index: 306491 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1182. Min Act: -0.0000

Data Index: 211010 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1105. Min Act: -0.0000

Data Index: 290511 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1061. Min Act: -0.0000

Data Index: 652277 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1179. Min Act: -0.0000

Data Index: 1075240 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1095. Min Act: -0.0000

Data Index: 1240196 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1123. Min Act: -0.0000

Data Index: 830238 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1144. Min Act: -0.0000

Data Index: 849897 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1101. Min Act: -0.0000

Data Index: 531882 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1130. Min Act: -0.0000

Data Index: 553776 (C4 (Web Text))

Max Activating Token Index: 718