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

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

Neuron 4102 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.5842. Min Act: 0.0001

Data Index: 313173 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1136949 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.5092. Min Act: -0.0000

Data Index: 725864 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4571. Min Act: 0.0000

Data Index: 927150 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.3510. Min Act: -0.0000

Data Index: 284869 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.3480. Min Act: 0.0001

Data Index: 369075 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.3408. Min Act: -0.0000

Data Index: 1269665 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.2911. Min Act: 0.0001

Data Index: 927385 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1404065 (Python Code)

Max Activating Token Index: 192

Text #9

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.2710. Min Act: 0.0002

Data Index: 444683 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1036845 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.2326. Min Act: -0.0000

Data Index: 1500474 (Python Code)

Max Activating Token Index: 848

Text #12

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.2457. Min Act: -0.0000

Data Index: 122142 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1148827 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.2385. Min Act: -0.0000

Data Index: 595263 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1504173 (Python Code)

Max Activating Token Index: 290

Text #16

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.2215. Min Act: -0.0000

Data Index: 610585 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1479885 (Python Code)

Max Activating Token Index: 856

Text #18

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.2206. Min Act: -0.0000

Data Index: 693055 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.2135. Min Act: -0.0000

Data Index: 8860 (C4 (Web Text))

Max Activating Token Index: 490