Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 576 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0423. Min Act: -0.0001

Data Index: 707856 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0254. Min Act: -0.0000

Data Index: 1234468 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0232. Min Act: -0.0001

Data Index: 233885 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0239. Min Act: -0.0000

Data Index: 450258 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0230. Min Act: -0.0001

Data Index: 616162 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0225. Min Act: -0.0001

Data Index: 844527 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0221. Min Act: -0.0001

Data Index: 821286 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1116640 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0234. Min Act: -0.0001

Data Index: 1308489 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0211. Min Act: -0.0001

Data Index: 1323523 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0227. Min Act: -0.0001

Data Index: 162441 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0203. Min Act: -0.0000

Data Index: 982480 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0177. Min Act: -0.0001

Data Index: 837666 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0184. Min Act: -0.0001

Data Index: 748769 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0200. Min Act: -0.0001

Data Index: 1038921 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0204. Min Act: -0.0001

Data Index: 611455 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0222. Min Act: -0.0001

Data Index: 1569257 (Python Code)

Max Activating Token Index: 631

Text #17

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0183. Min Act: -0.0001

Data Index: 775579 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0199. Min Act: -0.0001

Data Index: 1277229 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0193. Min Act: -0.0001

Data Index: 1154222 (C4 (Web Text))

Max Activating Token Index: 821