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

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

Neuron 1444 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.9515. Min Act: -0.0000

Data Index: 67997 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 1.0070. Min Range: -1.0070

Max Act: 1.0070. Min Act: -0.0000

Data Index: 646287 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.8837. Min Act: -0.0000

Data Index: 178613 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.9170. Min Act: -0.0000

Data Index: 234257 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.8222. Min Act: -0.0000

Data Index: 1055654 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.8581. Min Act: -0.0000

Data Index: 987049 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.8527. Min Act: -0.0000

Data Index: 353478 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.7434. Min Act: -0.0000

Data Index: 693397 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.8088. Min Act: -0.0000

Data Index: 321611 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.8101. Min Act: -0.0000

Data Index: 309742 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.7964. Min Act: -0.0000

Data Index: 826315 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.7225. Min Act: -0.0000

Data Index: 1288077 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.8126. Min Act: -0.0000

Data Index: 733773 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.7398. Min Act: -0.0000

Data Index: 401507 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.7370. Min Act: -0.0000

Data Index: 178946 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.7375. Min Act: -0.0000

Data Index: 308901 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.7400. Min Act: -0.0000

Data Index: 19559 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.7164. Min Act: -0.0000

Data Index: 931905 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.7296. Min Act: -0.0000

Data Index: 753327 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 1.0070. Min Range: -1.0070

Max Act: 0.6778. Min Act: -0.0000

Data Index: 549347 (C4 (Web Text))

Max Activating Token Index: 531