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

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

Neuron 674 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.6487. Min Act: -0.0000

Data Index: 1474329 (Python Code)

Max Activating Token Index: 93

Text #1

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1368838 (Python Code)

Max Activating Token Index: 532

Text #2

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4993. Min Act: 0.0000

Data Index: 1449355 (Python Code)

Max Activating Token Index: 638

Text #3

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4761. Min Act: 0.0000

Data Index: 1591210 (Python Code)

Max Activating Token Index: 518

Text #4

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4416. Min Act: 0.0000

Data Index: 1547223 (Python Code)

Max Activating Token Index: 1015

Text #5

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4341. Min Act: -0.0000

Data Index: 1639602 (Python Code)

Max Activating Token Index: 624

Text #6

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1478203 (Python Code)

Max Activating Token Index: 827

Text #7

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4016. Min Act: -0.0000

Data Index: 1595739 (Python Code)

Max Activating Token Index: 151

Text #8

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.4119. Min Act: 0.0000

Data Index: 1605951 (Python Code)

Max Activating Token Index: 201

Text #9

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1650238 (Python Code)

Max Activating Token Index: 448

Text #10

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.3669. Min Act: -0.0000

Data Index: 1590070 (Python Code)

Max Activating Token Index: 926

Text #11

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.3572. Min Act: -0.0000

Data Index: 1617798 (Python Code)

Max Activating Token Index: 654

Text #12

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1426806 (Python Code)

Max Activating Token Index: 402

Text #13

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1654065 (Python Code)

Max Activating Token Index: 958

Text #14

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.3443. Min Act: -0.0000

Data Index: 1547929 (Python Code)

Max Activating Token Index: 545

Text #15

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.3630. Min Act: -0.0000

Data Index: 1533580 (Python Code)

Max Activating Token Index: 140

Text #16

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.3750. Min Act: -0.0000

Data Index: 1509088 (Python Code)

Max Activating Token Index: 32

Text #17

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.3468. Min Act: -0.0000

Data Index: 1465857 (Python Code)

Max Activating Token Index: 938

Text #18

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1453958 (Python Code)

Max Activating Token Index: 899

Text #19

Max Range: 0.6487. Min Range: -0.6487

Max Act: 0.3646. Min Act: -0.0000

Data Index: 1572688 (Python Code)

Max Activating Token Index: 998