Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1246 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1537. Min Act: -0.0003

Data Index: 1215005 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1532. Min Act: -0.0003

Data Index: 1068325 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1371. Min Act: -0.0004

Data Index: 597627 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1346. Min Act: -0.0003

Data Index: 1232826 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1339. Min Act: -0.0003

Data Index: 1259211 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1319. Min Act: -0.0003

Data Index: 62473 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1309. Min Act: -0.0003

Data Index: 927182 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1301. Min Act: -0.0003

Data Index: 524963 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1264. Min Act: -0.0003

Data Index: 435107 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1311. Min Act: -0.0003

Data Index: 295109 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1309. Min Act: -0.0003

Data Index: 320741 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1278. Min Act: -0.0003

Data Index: 14516 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1293. Min Act: -0.0003

Data Index: 758066 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1231. Min Act: -0.0002

Data Index: 378240 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1233. Min Act: -0.0003

Data Index: 250077 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1220. Min Act: -0.0004

Data Index: 1477173 (Python Code)

Max Activating Token Index: 175

Text #16

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1205. Min Act: -0.0003

Data Index: 760364 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1258. Min Act: -0.0003

Data Index: 311933 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1142. Min Act: -0.0003

Data Index: 659335 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1205. Min Act: -0.0003

Data Index: 853613 (C4 (Web Text))

Max Activating Token Index: 827