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

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

Neuron 1589 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2331. Min Act: -0.0001

Data Index: 1592085 (Python Code)

Max Activating Token Index: 418

Text #1

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2283. Min Act: -0.0001

Data Index: 1392936 (Python Code)

Max Activating Token Index: 585

Text #2

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2217. Min Act: -0.0001

Data Index: 1612544 (Python Code)

Max Activating Token Index: 380

Text #3

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2223. Min Act: -0.0001

Data Index: 1412550 (Python Code)

Max Activating Token Index: 662

Text #4

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2221. Min Act: -0.0001

Data Index: 1628913 (Python Code)

Max Activating Token Index: 557

Text #5

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2174. Min Act: -0.0001

Data Index: 1391186 (Python Code)

Max Activating Token Index: 740

Text #6

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2186. Min Act: -0.0001

Data Index: 1559738 (Python Code)

Max Activating Token Index: 459

Text #7

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2210. Min Act: -0.0001

Data Index: 1390009 (Python Code)

Max Activating Token Index: 682

Text #8

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2187. Min Act: -0.0001

Data Index: 1472124 (Python Code)

Max Activating Token Index: 412

Text #9

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2205. Min Act: -0.0001

Data Index: 1461931 (Python Code)

Max Activating Token Index: 367

Text #10

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2159. Min Act: -0.0001

Data Index: 1375694 (Python Code)

Max Activating Token Index: 903

Text #11

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2184. Min Act: -0.0001

Data Index: 1530349 (Python Code)

Max Activating Token Index: 95

Text #12

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2148. Min Act: -0.0001

Data Index: 1609553 (Python Code)

Max Activating Token Index: 253

Text #13

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2190. Min Act: -0.0001

Data Index: 1479285 (Python Code)

Max Activating Token Index: 754

Text #14

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2142. Min Act: -0.0001

Data Index: 1507440 (Python Code)

Max Activating Token Index: 335

Text #15

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2134. Min Act: -0.0001

Data Index: 1366928 (Python Code)

Max Activating Token Index: 80

Text #16

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2135. Min Act: -0.0001

Data Index: 1581521 (Python Code)

Max Activating Token Index: 462

Text #17

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2119. Min Act: -0.0001

Data Index: 183176 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2125. Min Act: -0.0001

Data Index: 165763 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2104. Min Act: -0.0001

Data Index: 1547095 (Python Code)

Max Activating Token Index: 707