Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4859 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.4776. Min Act: -0.0000

Data Index: 859044 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3814. Min Act: -0.0001

Data Index: 1374825 (Python Code)

Max Activating Token Index: 328

Text #2

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1557465 (Python Code)

Max Activating Token Index: 181

Text #3

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1437280 (Python Code)

Max Activating Token Index: 945

Text #4

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1191864 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3605. Min Act: -0.0000

Data Index: 786022 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1622599 (Python Code)

Max Activating Token Index: 251

Text #7

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3511. Min Act: -0.0000

Data Index: 42075 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3634. Min Act: -0.0000

Data Index: 958926 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1024561 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1083759 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1573110 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3266. Min Act: -0.0000

Data Index: 1579407 (Python Code)

Max Activating Token Index: 734

Text #13

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3421. Min Act: -0.0000

Data Index: 296487 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3243. Min Act: -0.0000

Data Index: 122121 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3088. Min Act: -0.0000

Data Index: 617480 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3155. Min Act: -0.0000

Data Index: 530517 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1656300 (Python Code)

Max Activating Token Index: 979

Text #18

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.2844. Min Act: -0.0000

Data Index: 386991 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.2927. Min Act: -0.0000

Data Index: 174024 (C4 (Web Text))

Max Activating Token Index: 408