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

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

Neuron 2786 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.2036. Min Act: -0.0000

Data Index: 8270 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.1635. Min Act: -0.0000

Data Index: 137001 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.1694. Min Act: -0.0000

Data Index: 252949 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0646. Min Act: -0.0000

Data Index: 364677 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.1634. Min Act: -0.0000

Data Index: 219069 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0904. Min Act: -0.0000

Data Index: 1349547 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9724. Min Act: -0.0000

Data Index: 99443 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0167. Min Act: -0.0000

Data Index: 630587 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0032. Min Act: -0.0000

Data Index: 1158017 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9969. Min Act: -0.0000

Data Index: 815779 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1032666 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0403. Min Act: -0.0000

Data Index: 506808 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9128. Min Act: -0.0000

Data Index: 1189140 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9602. Min Act: -0.0000

Data Index: 505869 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0701. Min Act: -0.0000

Data Index: 901506 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.9222. Min Act: -0.0000

Data Index: 102938 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8934. Min Act: -0.0000

Data Index: 1300618 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 1.2036. Min Range: -1.2036

Max Act: 1.0008. Min Act: -0.0000

Data Index: 639293 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8927. Min Act: -0.0000

Data Index: 663951 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 1.2036. Min Range: -1.2036

Max Act: 0.8897. Min Act: -0.0000

Data Index: 375778 (C4 (Web Text))

Max Activating Token Index: 483