Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4141 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.5118. Min Act: -0.0000

Data Index: 597370 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1031594 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1197281 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.4125. Min Act: -0.0000

Data Index: 369857 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3953. Min Act: -0.0000

Data Index: 266426 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3795. Min Act: -0.0000

Data Index: 189661 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3899. Min Act: -0.0000

Data Index: 282262 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3644. Min Act: -0.0000

Data Index: 505230 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3731. Min Act: -0.0000

Data Index: 1224829 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3413. Min Act: -0.0000

Data Index: 46781 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3667. Min Act: -0.0000

Data Index: 497676 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1235791 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3313. Min Act: 0.0000

Data Index: 483193 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3371. Min Act: -0.0000

Data Index: 64523 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3417. Min Act: -0.0000

Data Index: 850468 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3209. Min Act: -0.0000

Data Index: 535492 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1331536 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3265. Min Act: -0.0000

Data Index: 552653 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3218. Min Act: -0.0000

Data Index: 802945 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 0.5118. Min Range: -0.5118

Max Act: 0.3287. Min Act: -0.0000

Data Index: 931762 (C4 (Web Text))

Max Activating Token Index: 891