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

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

Neuron 3070 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 3.7493. Min Range: -3.7493

Max Act: 3.7493. Min Act: -0.0002

Data Index: 232569 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 3.7493. Min Range: -3.7493

Max Act: 3.5797. Min Act: -0.0002

Data Index: 98100 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 3.7493. Min Range: -3.7493

Max Act: 3.6025. Min Act: -0.0002

Data Index: 757528 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 3.7493. Min Range: -3.7493

Max Act: 3.5626. Min Act: -0.0002

Data Index: 615903 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 3.7493. Min Range: -3.7493

Max Act: 3.2496. Min Act: -0.0002

Data Index: 315670 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 3.7493. Min Range: -3.7493

Max Act: 3.2831. Min Act: -0.0002

Data Index: 827100 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 3.7493. Min Range: -3.7493

Max Act: 3.2780. Min Act: -0.0002

Data Index: 324278 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 3.7493. Min Range: -3.7493

Max Act: 3.1851. Min Act: -0.0002

Data Index: 121092 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 3.7493. Min Range: -3.7493

Max Act: 3.1615. Min Act: -0.0002

Data Index: 353938 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 3.7493. Min Range: -3.7493

Max Act: 3.1622. Min Act: -0.0002

Data Index: 60989 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 3.7493. Min Range: -3.7493

Max Act: 3.2095. Min Act: -0.0002

Data Index: 554221 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 3.7493. Min Range: -3.7493

Max Act: 3.1565. Min Act: -0.0002

Data Index: 698150 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 3.7493. Min Range: -3.7493

Max Act: 3.1597. Min Act: -0.0002

Data Index: 1039838 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 3.7493. Min Range: -3.7493

Max Act: 3.0576. Min Act: -0.0002

Data Index: 1079509 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 3.7493. Min Range: -3.7493

Max Act: 3.1052. Min Act: -0.0002

Data Index: 1275106 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 3.7493. Min Range: -3.7493

Max Act: 2.9665. Min Act: -0.0002

Data Index: 69975 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 3.7493. Min Range: -3.7493

Max Act: 2.9205. Min Act: -0.0002

Data Index: 1015786 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 3.7493. Min Range: -3.7493

Max Act: 2.8804. Min Act: -0.0002

Data Index: 144252 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 3.7493. Min Range: -3.7493

Max Act: 2.9655. Min Act: -0.0002

Data Index: 768935 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 3.7493. Min Range: -3.7493

Max Act: 2.8396. Min Act: -0.0002

Data Index: 22825 (C4 (Web Text))

Max Activating Token Index: 825