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

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

Neuron 3070 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0003

Data Index: 486817 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0508. Min Act: -0.0003

Data Index: 785689 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0487. Min Act: -0.0003

Data Index: 964505 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0502. Min Act: -0.0003

Data Index: 662080 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0455. Min Act: -0.0003

Data Index: 123276 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0490. Min Act: -0.0003

Data Index: 363908 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0461. Min Act: -0.0003

Data Index: 203479 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0447. Min Act: -0.0003

Data Index: 245901 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0521. Min Act: -0.0003

Data Index: 654314 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0444. Min Act: -0.0003

Data Index: 238867 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0394. Min Act: -0.0003

Data Index: 73591 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0358. Min Act: -0.0003

Data Index: 268237 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0418. Min Act: -0.0003

Data Index: 787809 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0372. Min Act: -0.0003

Data Index: 259161 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0422. Min Act: -0.0003

Data Index: 102151 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0392. Min Act: -0.0003

Data Index: 852027 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1199752 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0425. Min Act: -0.0003

Data Index: 922796 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0398. Min Act: -0.0003

Data Index: 97061 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0401. Min Act: -0.0003

Data Index: 346993 (C4 (Web Text))

Max Activating Token Index: 118