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

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

Neuron 5126 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.8998. Min Range: -8.8998

Max Act: 8.8998. Min Act: -0.0000

Data Index: 236063 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 8.8998. Min Range: -8.8998

Max Act: 8.0543. Min Act: -0.0000

Data Index: 210461 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 8.8998. Min Range: -8.8998

Max Act: 8.0357. Min Act: -0.0000

Data Index: 801127 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 8.8998. Min Range: -8.8998

Max Act: 8.1821. Min Act: -0.0000

Data Index: 384946 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 8.8998. Min Range: -8.8998

Max Act: 8.3419. Min Act: -0.0000

Data Index: 448564 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 8.8998. Min Range: -8.8998

Max Act: 8.1481. Min Act: -0.0000

Data Index: 607689 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 8.8998. Min Range: -8.8998

Max Act: 7.7948. Min Act: -0.0000

Data Index: 1222714 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 8.8998. Min Range: -8.8998

Max Act: 8.0554. Min Act: -0.0000

Data Index: 1335757 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 8.8998. Min Range: -8.8998

Max Act: 7.9835. Min Act: -0.0000

Data Index: 609779 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 8.8998. Min Range: -8.8998

Max Act: 7.8151. Min Act: -0.0000

Data Index: 499374 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 8.8998. Min Range: -8.8998

Max Act: 7.7740. Min Act: -0.0000

Data Index: 1298831 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 8.8998. Min Range: -8.8998

Max Act: 7.5665. Min Act: -0.0000

Data Index: 1231212 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 8.8998. Min Range: -8.8998

Max Act: 7.5802. Min Act: -0.0000

Data Index: 294390 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 8.8998. Min Range: -8.8998

Max Act: 7.3954. Min Act: -0.0000

Data Index: 226094 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 8.8998. Min Range: -8.8998

Max Act: 7.5550. Min Act: -0.0000

Data Index: 124597 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 8.8998. Min Range: -8.8998

Max Act: 7.3355. Min Act: -0.0000

Data Index: 1087330 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 8.8998. Min Range: -8.8998

Max Act: 7.7172. Min Act: -0.0000

Data Index: 642576 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 8.8998. Min Range: -8.8998

Max Act: 7.5135. Min Act: -0.0000

Data Index: 1014224 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 8.8998. Min Range: -8.8998

Max Act: 7.3170. Min Act: -0.0000

Data Index: 340871 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 8.8998. Min Range: -8.8998

Max Act: 7.2613. Min Act: -0.0000

Data Index: 738589 (C4 (Web Text))

Max Activating Token Index: 41