Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1503 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 5.1664. Min Range: -5.1664

Max Act: 5.1664. Min Act: -0.0001

Data Index: 887919 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 5.1664. Min Range: -5.1664

Max Act: 4.9708. Min Act: -0.0001

Data Index: 334694 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 5.1664. Min Range: -5.1664

Max Act: 4.6605. Min Act: -0.0001

Data Index: 65772 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 5.1664. Min Range: -5.1664

Max Act: 4.4220. Min Act: -0.0001

Data Index: 231309 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 5.1664. Min Range: -5.1664

Max Act: 4.3371. Min Act: -0.0001

Data Index: 479975 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 5.1664. Min Range: -5.1664

Max Act: 4.3208. Min Act: -0.0001

Data Index: 991202 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 5.1664. Min Range: -5.1664

Max Act: 4.2673. Min Act: -0.0001

Data Index: 605039 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 5.1664. Min Range: -5.1664

Max Act: 4.2638. Min Act: -0.0001

Data Index: 1220370 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 5.1664. Min Range: -5.1664

Max Act: 4.3819. Min Act: -0.0001

Data Index: 96312 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 5.1664. Min Range: -5.1664

Max Act: 4.0346. Min Act: -0.0001

Data Index: 961001 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 5.1664. Min Range: -5.1664

Max Act: 4.2608. Min Act: -0.0001

Data Index: 492423 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 5.1664. Min Range: -5.1664

Max Act: 4.2600. Min Act: -0.0001

Data Index: 829079 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 5.1664. Min Range: -5.1664

Max Act: 4.0075. Min Act: -0.0001

Data Index: 183434 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 5.1664. Min Range: -5.1664

Max Act: 4.0156. Min Act: -0.0001

Data Index: 363765 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 5.1664. Min Range: -5.1664

Max Act: 4.0005. Min Act: -0.0001

Data Index: 284975 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 5.1664. Min Range: -5.1664

Max Act: 3.9712. Min Act: -0.0001

Data Index: 434820 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 5.1664. Min Range: -5.1664

Max Act: 3.6450. Min Act: -0.0001

Data Index: 755770 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 5.1664. Min Range: -5.1664

Max Act: 3.7507. Min Act: -0.0001

Data Index: 1219151 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 5.1664. Min Range: -5.1664

Max Act: 3.7078. Min Act: -0.0001

Data Index: 325488 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 5.1664. Min Range: -5.1664

Max Act: 3.6534. Min Act: -0.0001

Data Index: 788864 (C4 (Web Text))

Max Activating Token Index: 274