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

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

Neuron 4290 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: 2.0526. Min Range: -2.0526

Max Act: 2.0526. Min Act: -0.0000

Data Index: 718247 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.9102. Min Act: -0.0000

Data Index: 1286542 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.8309. Min Act: -0.0000

Data Index: 819333 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.7778. Min Act: -0.0000

Data Index: 51389 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.7420. Min Act: -0.0000

Data Index: 1269379 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.7137. Min Act: -0.0000

Data Index: 846573 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.8202. Min Act: -0.0000

Data Index: 998836 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.7020. Min Act: -0.0000

Data Index: 713939 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.7940. Min Act: -0.0000

Data Index: 1290051 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.6742. Min Act: -0.0000

Data Index: 676581 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.6733. Min Act: -0.0000

Data Index: 262857 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.7580. Min Act: -0.0000

Data Index: 420837 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.6170. Min Act: -0.0000

Data Index: 1220429 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.7124. Min Act: -0.0000

Data Index: 877064 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.6863. Min Act: -0.0000

Data Index: 1156447 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.5649. Min Act: -0.0000

Data Index: 1213 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.5699. Min Act: -0.0000

Data Index: 194796 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.5530. Min Act: -0.0000

Data Index: 103514 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.6267. Min Act: -0.0000

Data Index: 429577 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.4514. Min Act: -0.0000

Data Index: 367350 (C4 (Web Text))

Max Activating Token Index: 644