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

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

Neuron 360 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.4307. Min Act: -0.0000

Data Index: 212670 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.4146. Min Act: 0.0000

Data Index: 955422 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3748. Min Act: -0.0001

Data Index: 223856 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3507. Min Act: -0.0001

Data Index: 229742 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3441. Min Act: -0.0001

Data Index: 118171 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3419. Min Act: -0.0001

Data Index: 535187 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3065. Min Act: -0.0001

Data Index: 195393 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3085. Min Act: -0.0001

Data Index: 795235 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2967. Min Act: -0.0000

Data Index: 893619 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3148. Min Act: -0.0001

Data Index: 479108 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3135. Min Act: -0.0000

Data Index: 135491 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2848. Min Act: -0.0000

Data Index: 5292 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.3221. Min Act: -0.0001

Data Index: 374078 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2904. Min Act: -0.0000

Data Index: 1150323 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2670. Min Act: -0.0000

Data Index: 779900 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2835. Min Act: -0.0001

Data Index: 372805 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2659. Min Act: -0.0001

Data Index: 565001 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2736. Min Act: -0.0001

Data Index: 1284342 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2806. Min Act: -0.0000

Data Index: 174768 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.4307. Min Range: -0.4307

Max Act: 0.2768. Min Act: -0.0001

Data Index: 856740 (C4 (Web Text))

Max Activating Token Index: 234