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

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

Neuron 4780 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: 0.1535. Min Range: -0.1535

Max Act: 0.1535. Min Act: -0.0000

Data Index: 778824 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1438. Min Act: -0.0000

Data Index: 811971 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1465. Min Act: -0.0000

Data Index: 334738 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1190867 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1385. Min Act: -0.0000

Data Index: 243194 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1430. Min Act: -0.0000

Data Index: 108416 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1364. Min Act: -0.0000

Data Index: 1077517 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1357. Min Act: -0.0000

Data Index: 758366 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1300. Min Act: -0.0000

Data Index: 1298425 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1332. Min Act: -0.0000

Data Index: 72031 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1135093 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1280. Min Act: -0.0000

Data Index: 780075 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1080283 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1076922 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1200. Min Act: -0.0000

Data Index: 67405 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1223. Min Act: -0.0000

Data Index: 597967 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1187. Min Act: -0.0000

Data Index: 771964 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1269778 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1104492 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1207. Min Act: -0.0000

Data Index: 361772 (C4 (Web Text))

Max Activating Token Index: 308