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

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

Neuron 988 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: 1.1754. Min Range: -1.1754

Max Act: 1.1754. Min Act: -0.0002

Data Index: 420302 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1494. Min Act: -0.0002

Data Index: 667830 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1319. Min Act: -0.0002

Data Index: 593729 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1435. Min Act: -0.0003

Data Index: 111461 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1328. Min Act: -0.0002

Data Index: 211140 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1546. Min Act: -0.0002

Data Index: 1131081 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1366. Min Act: -0.0002

Data Index: 459452 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1391. Min Act: -0.0002

Data Index: 907964 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1366. Min Act: -0.0003

Data Index: 552713 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1283. Min Act: -0.0002

Data Index: 479990 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1516. Min Act: -0.0002

Data Index: 435257 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1413. Min Act: -0.0002

Data Index: 1045330 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1192. Min Act: -0.0002

Data Index: 553013 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1215. Min Act: -0.0002

Data Index: 937382 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1009. Min Act: -0.0002

Data Index: 489599 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1135. Min Act: -0.0002

Data Index: 482926 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1097. Min Act: -0.0002

Data Index: 886435 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1157. Min Act: -0.0002

Data Index: 634155 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.1073. Min Act: -0.0002

Data Index: 339278 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 1.1754. Min Range: -1.1754

Max Act: 1.0947. Min Act: -0.0002

Data Index: 815352 (C4 (Web Text))

Max Activating Token Index: 171