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

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

Neuron 5510 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0304. Min Range: -3.0304

Max Act: 3.0135. Min Act: -0.0000

Data Index: 215576 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 3.0304. Min Range: -3.0304

Max Act: 2.7130. Min Act: -0.0000

Data Index: 157171 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 3.0304. Min Range: -3.0304

Max Act: 3.0304. Min Act: -0.0000

Data Index: 1356481 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 3.0304. Min Range: -3.0304

Max Act: 2.7615. Min Act: -0.0000

Data Index: 7279 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 3.0304. Min Range: -3.0304

Max Act: 2.5689. Min Act: -0.0000

Data Index: 999250 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 3.0304. Min Range: -3.0304

Max Act: 2.8434. Min Act: -0.0000

Data Index: 547891 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 3.0304. Min Range: -3.0304

Max Act: 2.6862. Min Act: -0.0000

Data Index: 729357 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 3.0304. Min Range: -3.0304

Max Act: 2.7557. Min Act: -0.0000

Data Index: 398806 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 3.0304. Min Range: -3.0304

Max Act: 2.5248. Min Act: -0.0000

Data Index: 1034613 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 3.0304. Min Range: -3.0304

Max Act: 2.7342. Min Act: -0.0000

Data Index: 271087 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 3.0304. Min Range: -3.0304

Max Act: 2.4789. Min Act: -0.0000

Data Index: 1332690 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 3.0304. Min Range: -3.0304

Max Act: 2.3812. Min Act: -0.0000

Data Index: 1173283 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 3.0304. Min Range: -3.0304

Max Act: 2.5102. Min Act: -0.0000

Data Index: 1274265 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 3.0304. Min Range: -3.0304

Max Act: 2.4485. Min Act: -0.0000

Data Index: 712296 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 3.0304. Min Range: -3.0304

Max Act: 2.6278. Min Act: -0.0000

Data Index: 504728 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 3.0304. Min Range: -3.0304

Max Act: 2.2995. Min Act: -0.0000

Data Index: 219320 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 3.0304. Min Range: -3.0304

Max Act: 2.6232. Min Act: -0.0000

Data Index: 152672 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 3.0304. Min Range: -3.0304

Max Act: 2.2439. Min Act: -0.0000

Data Index: 1003271 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 3.0304. Min Range: -3.0304

Max Act: 2.4710. Min Act: -0.0000

Data Index: 920208 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 3.0304. Min Range: -3.0304

Max Act: 2.4366. Min Act: -0.0000

Data Index: 462201 (C4 (Web Text))

Max Activating Token Index: 690