Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3016 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.8995. Min Act: -0.0001

Data Index: 938861 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7980. Min Act: -0.0001

Data Index: 834476 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.8230. Min Act: -0.0000

Data Index: 482588 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7285. Min Act: -0.0001

Data Index: 731548 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.6269. Min Act: -0.0001

Data Index: 1285869 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.6714. Min Act: -0.0001

Data Index: 463316 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.6260. Min Act: -0.0001

Data Index: 836981 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.6078. Min Act: -0.0001

Data Index: 1240409 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.5602. Min Act: -0.0001

Data Index: 1045487 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.5453. Min Act: -0.0001

Data Index: 809637 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.5876. Min Act: -0.0001

Data Index: 779533 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.5992. Min Act: -0.0000

Data Index: 761800 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.5644. Min Act: -0.0001

Data Index: 574781 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.5503. Min Act: -0.0001

Data Index: 1190355 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.5369. Min Act: -0.0001

Data Index: 90306 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.5483. Min Act: -0.0001

Data Index: 1098546 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.5238. Min Act: -0.0001

Data Index: 481248 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.5084. Min Act: -0.0001

Data Index: 358899 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.4877. Min Act: -0.0001

Data Index: 966636 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.5163. Min Act: -0.0001

Data Index: 251793 (C4 (Web Text))

Max Activating Token Index: 667