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

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

Neuron 2238 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.3261. Min Act: -0.0000

Data Index: 275158 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.3361. Min Act: -0.0000

Data Index: 152298 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.3334. Min Act: -0.0000

Data Index: 852931 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.2527. Min Act: -0.0000

Data Index: 429507 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.3276. Min Act: -0.0000

Data Index: 1336204 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.2413. Min Act: -0.0000

Data Index: 1187940 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.3121. Min Act: -0.0000

Data Index: 388376 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.3215. Min Act: -0.0000

Data Index: 883963 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.3131. Min Act: -0.0000

Data Index: 738958 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.2173. Min Act: -0.0000

Data Index: 477090 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.1543. Min Act: -0.0000

Data Index: 1051677 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.1718. Min Act: -0.0000

Data Index: 1040248 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.1137. Min Act: -0.0000

Data Index: 489081 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.0901. Min Act: -0.0000

Data Index: 605861 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.0130. Min Act: -0.0000

Data Index: 574795 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.0474. Min Act: -0.0000

Data Index: 804312 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.0010. Min Act: -0.0000

Data Index: 664187 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.0133. Min Act: -0.0000

Data Index: 151918 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 1.3361. Min Range: -1.3361

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1150908 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 1.3361. Min Range: -1.3361

Max Act: 1.0149. Min Act: -0.0000

Data Index: 980069 (C4 (Web Text))

Max Activating Token Index: 186