Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 137 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1863. Min Act: -0.0003

Data Index: 968752 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1721. Min Act: -0.0003

Data Index: 842940 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1722. Min Act: -0.0003

Data Index: 397486 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1751. Min Act: -0.0003

Data Index: 401225 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1673. Min Act: -0.0003

Data Index: 25280 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1716. Min Act: -0.0003

Data Index: 439344 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1617. Min Act: -0.0003

Data Index: 455276 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1623. Min Act: -0.0003

Data Index: 972930 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1557. Min Act: -0.0003

Data Index: 666610 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1573. Min Act: -0.0003

Data Index: 856414 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1613. Min Act: -0.0003

Data Index: 301297 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1552. Min Act: -0.0003

Data Index: 284590 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1414. Min Act: -0.0003

Data Index: 147328 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1463. Min Act: -0.0003

Data Index: 825043 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1494. Min Act: -0.0004

Data Index: 646640 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1487. Min Act: -0.0003

Data Index: 835063 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1500. Min Act: -0.0003

Data Index: 775091 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1446. Min Act: -0.0003

Data Index: 333228 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1426. Min Act: -0.0003

Data Index: 436784 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1543. Min Act: -0.0003

Data Index: 341611 (C4 (Web Text))

Max Activating Token Index: 947