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

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

Neuron 732 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: 0.1254. Min Range: -0.1254

Max Act: 0.1254. Min Act: -0.0000

Data Index: 496670 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1214. Min Act: -0.0000

Data Index: 54423 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1178. Min Act: -0.0000

Data Index: 941463 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1144. Min Act: -0.0000

Data Index: 805977 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1044. Min Act: -0.0000

Data Index: 842939 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1240694 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1052. Min Act: -0.0000

Data Index: 340859 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1021. Min Act: -0.0000

Data Index: 657170 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0998. Min Act: -0.0000

Data Index: 862166 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0996. Min Act: -0.0000

Data Index: 728342 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0952. Min Act: -0.0000

Data Index: 689916 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1045. Min Act: -0.0000

Data Index: 1164526 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1038. Min Act: -0.0000

Data Index: 796431 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0904. Min Act: -0.0000

Data Index: 1320675 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0899. Min Act: -0.0000

Data Index: 386679 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1331552 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1021328 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0887. Min Act: -0.0000

Data Index: 369215 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0943. Min Act: -0.0000

Data Index: 500266 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0900. Min Act: -0.0000

Data Index: 1303119 (C4 (Web Text))

Max Activating Token Index: 159