Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5466 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.9216. Min Act: -0.0000

Data Index: 503875 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.4086. Min Act: -0.0000

Data Index: 1398271 (Python Code)

Max Activating Token Index: 271

Text #2

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.5168. Min Act: -0.0000

Data Index: 1644159 (Python Code)

Max Activating Token Index: 425

Text #3

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.5096. Min Act: -0.0000

Data Index: 1427187 (Python Code)

Max Activating Token Index: 168

Text #4

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.4911. Min Act: -0.0000

Data Index: 1584841 (Python Code)

Max Activating Token Index: 438

Text #5

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.4010. Min Act: -0.0000

Data Index: 1371132 (Python Code)

Max Activating Token Index: 668

Text #6

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.5255. Min Act: -0.0000

Data Index: 1484155 (Python Code)

Max Activating Token Index: 251

Text #7

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.3914. Min Act: -0.0000

Data Index: 1369619 (Python Code)

Max Activating Token Index: 631

Text #8

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.4342. Min Act: -0.0000

Data Index: 1198161 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.3272. Min Act: -0.0000

Data Index: 364638 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.2763. Min Act: -0.0000

Data Index: 1568251 (Python Code)

Max Activating Token Index: 273

Text #11

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.2785. Min Act: -0.0000

Data Index: 430219 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.2283. Min Act: -0.0000

Data Index: 20007 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.3349. Min Act: -0.0000

Data Index: 195141 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.2512. Min Act: -0.0000

Data Index: 1570823 (Python Code)

Max Activating Token Index: 949

Text #15

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.3075. Min Act: -0.0000

Data Index: 1629937 (Python Code)

Max Activating Token Index: 147

Text #16

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.2176. Min Act: -0.0000

Data Index: 432715 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.1900. Min Act: -0.0000

Data Index: 423994 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.1848. Min Act: -0.0000

Data Index: 1435483 (Python Code)

Max Activating Token Index: 137

Text #19

Max Range: 1.9216. Min Range: -1.9216

Max Act: 1.2941. Min Act: -0.0000

Data Index: 1551297 (Python Code)

Max Activating Token Index: 126