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

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

Neuron 1193 in Layer 1

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: 1.4140. Min Range: -1.4140

Max Act: 1.4140. Min Act: -0.0002

Data Index: 213924 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 1.4140. Min Range: -1.4140

Max Act: 1.2542. Min Act: -0.0002

Data Index: 42161 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 1.4140. Min Range: -1.4140

Max Act: 1.2358. Min Act: -0.0002

Data Index: 1156258 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 1.4140. Min Range: -1.4140

Max Act: 1.2289. Min Act: -0.0002

Data Index: 102095 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 1.4140. Min Range: -1.4140

Max Act: 1.1949. Min Act: -0.0002

Data Index: 503308 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 1.4140. Min Range: -1.4140

Max Act: 1.1950. Min Act: -0.0002

Data Index: 1086086 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 1.4140. Min Range: -1.4140

Max Act: 1.1477. Min Act: -0.0002

Data Index: 1024355 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 1.4140. Min Range: -1.4140

Max Act: 1.1694. Min Act: -0.0002

Data Index: 46201 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 1.4140. Min Range: -1.4140

Max Act: 1.1380. Min Act: -0.0002

Data Index: 194273 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 1.4140. Min Range: -1.4140

Max Act: 1.1842. Min Act: -0.0002

Data Index: 1123917 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 1.4140. Min Range: -1.4140

Max Act: 1.1660. Min Act: -0.0002

Data Index: 701290 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 1.4140. Min Range: -1.4140

Max Act: 1.1307. Min Act: -0.0002

Data Index: 1014921 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 1.4140. Min Range: -1.4140

Max Act: 1.1559. Min Act: -0.0002

Data Index: 810459 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 1.4140. Min Range: -1.4140

Max Act: 1.1235. Min Act: -0.0003

Data Index: 1163984 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 1.4140. Min Range: -1.4140

Max Act: 1.1211. Min Act: -0.0002

Data Index: 660151 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 1.4140. Min Range: -1.4140

Max Act: 1.1134. Min Act: -0.0002

Data Index: 893838 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 1.4140. Min Range: -1.4140

Max Act: 1.0844. Min Act: -0.0002

Data Index: 218189 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 1.4140. Min Range: -1.4140

Max Act: 1.0981. Min Act: -0.0002

Data Index: 363640 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 1.4140. Min Range: -1.4140

Max Act: 1.1270. Min Act: -0.0002

Data Index: 483516 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 1.4140. Min Range: -1.4140

Max Act: 1.0994. Min Act: -0.0002

Data Index: 435936 (C4 (Web Text))

Max Activating Token Index: 87