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

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

Neuron 2563 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: 2.4414. Min Range: -2.4414

Max Act: 2.4414. Min Act: -0.0000

Data Index: 474184 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 2.4414. Min Range: -2.4414

Max Act: 2.2544. Min Act: -0.0000

Data Index: 290113 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 2.4414. Min Range: -2.4414

Max Act: 2.3262. Min Act: -0.0000

Data Index: 210698 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 2.4414. Min Range: -2.4414

Max Act: 2.0263. Min Act: 0.0000

Data Index: 880333 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 2.4414. Min Range: -2.4414

Max Act: 2.1308. Min Act: -0.0000

Data Index: 722044 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 2.4414. Min Range: -2.4414

Max Act: 2.1252. Min Act: 0.0001

Data Index: 749883 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 2.4414. Min Range: -2.4414

Max Act: 2.0773. Min Act: -0.0000

Data Index: 463595 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 2.4414. Min Range: -2.4414

Max Act: 2.0137. Min Act: -0.0000

Data Index: 307348 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 2.4414. Min Range: -2.4414

Max Act: 2.0019. Min Act: -0.0000

Data Index: 546788 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 2.4414. Min Range: -2.4414

Max Act: 1.9893. Min Act: -0.0000

Data Index: 968252 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 2.4414. Min Range: -2.4414

Max Act: 2.1125. Min Act: -0.0000

Data Index: 1449074 (Python Code)

Max Activating Token Index: 903

Text #11

Max Range: 2.4414. Min Range: -2.4414

Max Act: 1.8712. Min Act: 0.0000

Data Index: 1216672 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 2.4414. Min Range: -2.4414

Max Act: 1.9431. Min Act: -0.0000

Data Index: 10018 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 2.4414. Min Range: -2.4414

Max Act: 1.9359. Min Act: -0.0000

Data Index: 521304 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 2.4414. Min Range: -2.4414

Max Act: 1.9318. Min Act: -0.0000

Data Index: 285936 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 2.4414. Min Range: -2.4414

Max Act: 1.9289. Min Act: -0.0000

Data Index: 24573 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 2.4414. Min Range: -2.4414

Max Act: 1.9129. Min Act: -0.0000

Data Index: 1270137 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 2.4414. Min Range: -2.4414

Max Act: 1.9114. Min Act: -0.0000

Data Index: 1617752 (Python Code)

Max Activating Token Index: 776

Text #18

Max Range: 2.4414. Min Range: -2.4414

Max Act: 1.8967. Min Act: -0.0000

Data Index: 401730 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 2.4414. Min Range: -2.4414

Max Act: 1.8883. Min Act: -0.0000

Data Index: 814281 (C4 (Web Text))

Max Activating Token Index: 956