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

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

Neuron 2510 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1573. Min Range: -1.1573

Max Act: 1.1573. Min Act: -0.0001

Data Index: 4059 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.9642. Min Act: -0.0001

Data Index: 165277 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 1.1573. Min Range: -1.1573

Max Act: 1.0373. Min Act: -0.0001

Data Index: 219557 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.9508. Min Act: -0.0001

Data Index: 1211332 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8609. Min Act: -0.0001

Data Index: 202304 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8116. Min Act: -0.0001

Data Index: 111615 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8365. Min Act: -0.0001

Data Index: 995781 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8425. Min Act: -0.0001

Data Index: 604960 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8518. Min Act: -0.0001

Data Index: 3412 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8825. Min Act: -0.0001

Data Index: 473870 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8445. Min Act: -0.0001

Data Index: 269219 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8812. Min Act: -0.0001

Data Index: 859939 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8515. Min Act: -0.0001

Data Index: 841932 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8472. Min Act: -0.0001

Data Index: 191639 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8507. Min Act: -0.0001

Data Index: 635930 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8182. Min Act: -0.0001

Data Index: 234102 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8495. Min Act: -0.0001

Data Index: 964238 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8429. Min Act: -0.0001

Data Index: 1212465 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8593. Min Act: -0.0001

Data Index: 184557 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8123. Min Act: -0.0001

Data Index: 1359494 (C4 (Web Text))

Max Activating Token Index: 525