Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 585 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.4492. Min Act: -0.0000

Data Index: 369371 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.3346. Min Act: -0.0000

Data Index: 740212 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 3.4492. Min Range: -3.4492

Max Act: 2.7869. Min Act: -0.0000

Data Index: 113943 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.0344. Min Act: -0.0000

Data Index: 905105 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 3.4492. Min Range: -3.4492

Max Act: 2.9947. Min Act: -0.0000

Data Index: 796723 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 3.4492. Min Range: -3.4492

Max Act: 2.9770. Min Act: -0.0000

Data Index: 906247 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 3.4492. Min Range: -3.4492

Max Act: 2.5423. Min Act: -0.0000

Data Index: 1019990 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 3.4492. Min Range: -3.4492

Max Act: 2.9342. Min Act: -0.0000

Data Index: 146679 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 3.4492. Min Range: -3.4492

Max Act: 2.6441. Min Act: -0.0000

Data Index: 346205 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.0246. Min Act: -0.0000

Data Index: 898056 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 3.4492. Min Range: -3.4492

Max Act: 2.8719. Min Act: -0.0000

Data Index: 605850 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 3.4492. Min Range: -3.4492

Max Act: 2.5888. Min Act: -0.0000

Data Index: 153394 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 3.4492. Min Range: -3.4492

Max Act: 2.7910. Min Act: -0.0000

Data Index: 702422 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 3.4492. Min Range: -3.4492

Max Act: 2.7186. Min Act: -0.0000

Data Index: 320733 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 3.4492. Min Range: -3.4492

Max Act: 2.7094. Min Act: -0.0000

Data Index: 234563 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 3.4492. Min Range: -3.4492

Max Act: 2.7110. Min Act: -0.0000

Data Index: 1343462 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 3.4492. Min Range: -3.4492

Max Act: 2.8227. Min Act: -0.0000

Data Index: 1348097 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 3.4492. Min Range: -3.4492

Max Act: 2.6213. Min Act: -0.0000

Data Index: 436488 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 3.4492. Min Range: -3.4492

Max Act: 2.6192. Min Act: -0.0000

Data Index: 1067880 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 3.4492. Min Range: -3.4492

Max Act: 2.4704. Min Act: -0.0000

Data Index: 393993 (C4 (Web Text))

Max Activating Token Index: 1004