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

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

Neuron 1146 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1467. Min Range: -4.1467

Max Act: 4.1467. Min Act: -0.0000

Data Index: 1289460 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 4.1467. Min Range: -4.1467

Max Act: 3.6964. Min Act: -0.0000

Data Index: 963484 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 4.1467. Min Range: -4.1467

Max Act: 3.2298. Min Act: -0.0000

Data Index: 740584 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 4.1467. Min Range: -4.1467

Max Act: 3.3453. Min Act: -0.0000

Data Index: 245851 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 4.1467. Min Range: -4.1467

Max Act: 3.3124. Min Act: -0.0000

Data Index: 377598 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 4.1467. Min Range: -4.1467

Max Act: 3.1630. Min Act: -0.0000

Data Index: 214518 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 4.1467. Min Range: -4.1467

Max Act: 3.1812. Min Act: -0.0000

Data Index: 51937 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 4.1467. Min Range: -4.1467

Max Act: 3.1781. Min Act: -0.0000

Data Index: 400230 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 4.1467. Min Range: -4.1467

Max Act: 3.0225. Min Act: -0.0000

Data Index: 499316 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 4.1467. Min Range: -4.1467

Max Act: 3.1587. Min Act: -0.0000

Data Index: 1320083 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 4.1467. Min Range: -4.1467

Max Act: 2.8385. Min Act: -0.0000

Data Index: 1109201 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 4.1467. Min Range: -4.1467

Max Act: 2.9410. Min Act: -0.0000

Data Index: 474478 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 4.1467. Min Range: -4.1467

Max Act: 2.8178. Min Act: -0.0000

Data Index: 1155564 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 4.1467. Min Range: -4.1467

Max Act: 2.8216. Min Act: -0.0000

Data Index: 900446 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 4.1467. Min Range: -4.1467

Max Act: 2.8901. Min Act: -0.0000

Data Index: 1295616 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 4.1467. Min Range: -4.1467

Max Act: 2.8524. Min Act: -0.0000

Data Index: 1307458 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 4.1467. Min Range: -4.1467

Max Act: 2.8139. Min Act: -0.0000

Data Index: 456429 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 4.1467. Min Range: -4.1467

Max Act: 2.7302. Min Act: -0.0000

Data Index: 330992 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 4.1467. Min Range: -4.1467

Max Act: 2.8338. Min Act: -0.0000

Data Index: 380236 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 4.1467. Min Range: -4.1467

Max Act: 2.8197. Min Act: -0.0000

Data Index: 1031816 (C4 (Web Text))

Max Activating Token Index: 214