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

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

Neuron 3264 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1196. Min Act: -0.0001

Data Index: 966624 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1228. Min Act: -0.0000

Data Index: 313507 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1104. Min Act: -0.0001

Data Index: 26996 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1052. Min Act: -0.0001

Data Index: 345994 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1136. Min Act: -0.0001

Data Index: 1117880 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1040. Min Act: -0.0000

Data Index: 120503 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0998. Min Act: -0.0000

Data Index: 455466 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1037. Min Act: -0.0000

Data Index: 887579 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1023. Min Act: -0.0001

Data Index: 746755 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0970. Min Act: -0.0001

Data Index: 709155 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1075. Min Act: -0.0000

Data Index: 153396 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0986. Min Act: -0.0001

Data Index: 1100597 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0952. Min Act: -0.0000

Data Index: 299438 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1093954 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1231140 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1013. Min Act: -0.0000

Data Index: 506126 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1038. Min Act: -0.0000

Data Index: 1267452 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0933. Min Act: -0.0001

Data Index: 31685 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0928. Min Act: -0.0001

Data Index: 230461 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0919. Min Act: -0.0001

Data Index: 248640 (C4 (Web Text))

Max Activating Token Index: 1000