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

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

Neuron 4029 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0173. Min Range: -2.0173

Max Act: 2.0173. Min Act: -0.0000

Data Index: 1601548 (Python Code)

Max Activating Token Index: 461

Text #1

Max Range: 2.0173. Min Range: -2.0173

Max Act: 1.6921. Min Act: -0.0000

Data Index: 1424734 (Python Code)

Max Activating Token Index: 568

Text #2

Max Range: 2.0173. Min Range: -2.0173

Max Act: 1.6977. Min Act: -0.0000

Data Index: 1645632 (Python Code)

Max Activating Token Index: 221

Text #3

Max Range: 2.0173. Min Range: -2.0173

Max Act: 1.5434. Min Act: -0.0000

Data Index: 1588089 (Python Code)

Max Activating Token Index: 947

Text #4

Max Range: 2.0173. Min Range: -2.0173

Max Act: 1.3040. Min Act: -0.0000

Data Index: 1380818 (Python Code)

Max Activating Token Index: 447

Text #5

Max Range: 2.0173. Min Range: -2.0173

Max Act: 0.9922. Min Act: -0.0000

Data Index: 1539373 (Python Code)

Max Activating Token Index: 309

Text #6

Max Range: 2.0173. Min Range: -2.0173

Max Act: 1.0546. Min Act: -0.0000

Data Index: 1607090 (Python Code)

Max Activating Token Index: 457

Text #7

Max Range: 2.0173. Min Range: -2.0173

Max Act: 0.9795. Min Act: -0.0000

Data Index: 1381045 (Python Code)

Max Activating Token Index: 903

Text #8

Max Range: 2.0173. Min Range: -2.0173

Max Act: 1.0153. Min Act: -0.0000

Data Index: 1552643 (Python Code)

Max Activating Token Index: 365

Text #9

Max Range: 2.0173. Min Range: -2.0173

Max Act: 0.9584. Min Act: -0.0000

Data Index: 1632291 (Python Code)

Max Activating Token Index: 817

Text #10

Max Range: 2.0173. Min Range: -2.0173

Max Act: 1.0477. Min Act: -0.0000

Data Index: 1552099 (Python Code)

Max Activating Token Index: 533

Text #11

Max Range: 2.0173. Min Range: -2.0173

Max Act: 0.9501. Min Act: -0.0000

Data Index: 1541151 (Python Code)

Max Activating Token Index: 296

Text #12

Max Range: 2.0173. Min Range: -2.0173

Max Act: 1.1120. Min Act: -0.0000

Data Index: 1506454 (Python Code)

Max Activating Token Index: 416

Text #13

Max Range: 2.0173. Min Range: -2.0173

Max Act: 1.0378. Min Act: -0.0000

Data Index: 1632701 (Python Code)

Max Activating Token Index: 698

Text #14

Max Range: 2.0173. Min Range: -2.0173

Max Act: 0.9723. Min Act: -0.0000

Data Index: 1638282 (Python Code)

Max Activating Token Index: 939

Text #15

Max Range: 2.0173. Min Range: -2.0173

Max Act: 0.9585. Min Act: -0.0000

Data Index: 1615523 (Python Code)

Max Activating Token Index: 609

Text #16

Max Range: 2.0173. Min Range: -2.0173

Max Act: 0.9817. Min Act: -0.0000

Data Index: 1652325 (Python Code)

Max Activating Token Index: 477

Text #17

Max Range: 2.0173. Min Range: -2.0173

Max Act: 0.9445. Min Act: -0.0000

Data Index: 1437192 (Python Code)

Max Activating Token Index: 525

Text #18

Max Range: 2.0173. Min Range: -2.0173

Max Act: 1.1259. Min Act: -0.0000

Data Index: 1427560 (Python Code)

Max Activating Token Index: 217

Text #19

Max Range: 2.0173. Min Range: -2.0173

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1484441 (Python Code)

Max Activating Token Index: 573