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

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

Neuron 698 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1296. Min Act: -0.0001

Data Index: 512099 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1344890 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1121. Min Act: -0.0001

Data Index: 225456 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1050. Min Act: -0.0001

Data Index: 374076 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1383290 (Python Code)

Max Activating Token Index: 502

Text #5

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0974. Min Act: -0.0001

Data Index: 1597546 (Python Code)

Max Activating Token Index: 145

Text #6

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1109. Min Act: -0.0002

Data Index: 1256725 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1032. Min Act: -0.0001

Data Index: 827064 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0983. Min Act: -0.0001

Data Index: 250059 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0982. Min Act: -0.0002

Data Index: 1336908 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1037. Min Act: -0.0001

Data Index: 936382 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1053. Min Act: -0.0001

Data Index: 1123610 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1082. Min Act: -0.0001

Data Index: 293642 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1431040 (Python Code)

Max Activating Token Index: 646

Text #14

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1090. Min Act: -0.0001

Data Index: 1220229 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1110. Min Act: -0.0001

Data Index: 267967 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0829. Min Act: -0.0002

Data Index: 284088 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0947. Min Act: -0.0001

Data Index: 780057 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0777. Min Act: -0.0002

Data Index: 914186 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1367297 (Python Code)

Max Activating Token Index: 953