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

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

Neuron 140 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.8415. Min Act: -0.0001

Data Index: 441434 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1290839 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7106. Min Act: -0.0000

Data Index: 400511 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7210. Min Act: -0.0001

Data Index: 827548 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1145960 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1076493 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6620. Min Act: -0.0000

Data Index: 47458 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7074. Min Act: -0.0000

Data Index: 252977 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7066. Min Act: -0.0000

Data Index: 1235310 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6866. Min Act: -0.0000

Data Index: 445153 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7034. Min Act: -0.0000

Data Index: 928583 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7035. Min Act: -0.0000

Data Index: 584456 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1069508 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7048. Min Act: -0.0001

Data Index: 109942 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6983. Min Act: -0.0001

Data Index: 112112 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6996. Min Act: -0.0000

Data Index: 701310 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7209. Min Act: -0.0001

Data Index: 1156609 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7190. Min Act: -0.0000

Data Index: 872689 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.7185. Min Act: -0.0001

Data Index: 695943 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 0.8415. Min Range: -0.8415

Max Act: 0.6714. Min Act: -0.0001

Data Index: 621640 (C4 (Web Text))

Max Activating Token Index: 121