Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 734 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.8399. Min Act: -0.0001

Data Index: 1634880 (Python Code)

Max Activating Token Index: 112

Text #1

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.8923. Min Act: -0.0001

Data Index: 1638240 (Python Code)

Max Activating Token Index: 72

Text #2

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.4673. Min Act: -0.0001

Data Index: 1419469 (Python Code)

Max Activating Token Index: 747

Text #3

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.4532. Min Act: -0.0001

Data Index: 1426422 (Python Code)

Max Activating Token Index: 590

Text #4

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.4631. Min Act: -0.0001

Data Index: 1647271 (Python Code)

Max Activating Token Index: 832

Text #5

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.6185. Min Act: -0.0001

Data Index: 1512465 (Python Code)

Max Activating Token Index: 1008

Text #6

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.5360. Min Act: -0.0001

Data Index: 1548148 (Python Code)

Max Activating Token Index: 117

Text #7

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.4332. Min Act: -0.0001

Data Index: 1541954 (Python Code)

Max Activating Token Index: 665

Text #8

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.4415. Min Act: -0.0001

Data Index: 1540874 (Python Code)

Max Activating Token Index: 868

Text #9

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.3970. Min Act: -0.0001

Data Index: 1560048 (Python Code)

Max Activating Token Index: 827

Text #10

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.4112. Min Act: -0.0001

Data Index: 1647514 (Python Code)

Max Activating Token Index: 580

Text #11

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.3920. Min Act: -0.0001

Data Index: 1473381 (Python Code)

Max Activating Token Index: 656

Text #12

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.4601. Min Act: -0.0001

Data Index: 1378654 (Python Code)

Max Activating Token Index: 307

Text #13

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.4217. Min Act: -0.0001

Data Index: 1371806 (Python Code)

Max Activating Token Index: 227

Text #14

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.3814. Min Act: -0.0001

Data Index: 1418883 (Python Code)

Max Activating Token Index: 606

Text #15

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.3231. Min Act: -0.0001

Data Index: 1372320 (Python Code)

Max Activating Token Index: 801

Text #16

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.3597. Min Act: -0.0001

Data Index: 1626683 (Python Code)

Max Activating Token Index: 746

Text #17

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.3713. Min Act: -0.0001

Data Index: 1566568 (Python Code)

Max Activating Token Index: 308

Text #18

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.3629. Min Act: -0.0001

Data Index: 1447390 (Python Code)

Max Activating Token Index: 346

Text #19

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.3670. Min Act: -0.0001

Data Index: 1489116 (Python Code)

Max Activating Token Index: 560