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

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

Neuron 1581 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3481. Min Range: -5.3481

Max Act: 5.3481. Min Act: -0.0000

Data Index: 455525 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 5.3481. Min Range: -5.3481

Max Act: 4.8334. Min Act: -0.0000

Data Index: 630911 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 5.3481. Min Range: -5.3481

Max Act: 4.6845. Min Act: -0.0000

Data Index: 468519 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 5.3481. Min Range: -5.3481

Max Act: 4.6626. Min Act: -0.0000

Data Index: 352929 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 5.3481. Min Range: -5.3481

Max Act: 4.1026. Min Act: -0.0000

Data Index: 292586 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 5.3481. Min Range: -5.3481

Max Act: 4.3470. Min Act: -0.0000

Data Index: 934681 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 5.3481. Min Range: -5.3481

Max Act: 4.1670. Min Act: -0.0000

Data Index: 1068432 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 5.3481. Min Range: -5.3481

Max Act: 4.3110. Min Act: -0.0000

Data Index: 360473 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 5.3481. Min Range: -5.3481

Max Act: 4.3035. Min Act: -0.0000

Data Index: 420990 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 5.3481. Min Range: -5.3481

Max Act: 4.4817. Min Act: -0.0000

Data Index: 1215619 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 5.3481. Min Range: -5.3481

Max Act: 4.0851. Min Act: -0.0000

Data Index: 1191989 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 5.3481. Min Range: -5.3481

Max Act: 4.2210. Min Act: -0.0000

Data Index: 606297 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 5.3481. Min Range: -5.3481

Max Act: 4.1632. Min Act: -0.0000

Data Index: 663428 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 5.3481. Min Range: -5.3481

Max Act: 4.2839. Min Act: -0.0000

Data Index: 852550 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 5.3481. Min Range: -5.3481

Max Act: 4.1152. Min Act: -0.0000

Data Index: 1290394 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 5.3481. Min Range: -5.3481

Max Act: 3.9700. Min Act: -0.0000

Data Index: 452988 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 5.3481. Min Range: -5.3481

Max Act: 4.0908. Min Act: -0.0000

Data Index: 931983 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 5.3481. Min Range: -5.3481

Max Act: 3.9986. Min Act: -0.0000

Data Index: 981240 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 5.3481. Min Range: -5.3481

Max Act: 4.1278. Min Act: -0.0000

Data Index: 704240 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 5.3481. Min Range: -5.3481

Max Act: 4.1202. Min Act: -0.0000

Data Index: 116939 (C4 (Web Text))

Max Activating Token Index: 301