Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1634 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.2326. Min Act: -0.0002

Data Index: 255568 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.2048. Min Act: -0.0003

Data Index: 688505 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1384. Min Act: -0.0003

Data Index: 202733 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1257. Min Act: -0.0004

Data Index: 38959 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1511. Min Act: -0.0003

Data Index: 854993 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1257. Min Act: -0.0003

Data Index: 613234 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1015. Min Act: -0.0003

Data Index: 549142 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1225. Min Act: -0.0003

Data Index: 702775 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1030. Min Act: -0.0003

Data Index: 715111 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1161. Min Act: -0.0003

Data Index: 1223474 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1152. Min Act: -0.0003

Data Index: 888213 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1135. Min Act: -0.0003

Data Index: 223358 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1121. Min Act: -0.0003

Data Index: 685662 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1130. Min Act: -0.0004

Data Index: 1151322 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1097. Min Act: -0.0003

Data Index: 1656829 (Python Code)

Max Activating Token Index: 966

Text #15

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1018. Min Act: -0.0003

Data Index: 924660 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1099. Min Act: -0.0003

Data Index: 891510 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.0889. Min Act: -0.0003

Data Index: 1293918 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.0975. Min Act: -0.0003

Data Index: 1213664 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.0913. Min Act: -0.0003

Data Index: 1039709 (C4 (Web Text))

Max Activating Token Index: 181