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

Dataset: The Pile

Neuron 878 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 14.3512. Min Range: -14.3512

Max Act: 14.3512. Min Act: -0.0000

Data Index: 1992435 (The Pile)

Max Activating Token Index: 714

Text #1

Max Range: 14.3512. Min Range: -14.3512

Max Act: 14.0487. Min Act: -0.0000

Data Index: 243097 (The Pile)

Max Activating Token Index: 330

Text #2

Max Range: 14.3512. Min Range: -14.3512

Max Act: 14.0493. Min Act: -0.0000

Data Index: 1838604 (The Pile)

Max Activating Token Index: 405

Text #3

Max Range: 14.3512. Min Range: -14.3512

Max Act: 13.8930. Min Act: -0.0000

Data Index: 1527969 (The Pile)

Max Activating Token Index: 516

Text #4

Max Range: 14.3512. Min Range: -14.3512

Max Act: 13.7395. Min Act: -0.0000

Data Index: 1251544 (The Pile)

Max Activating Token Index: 632

Text #5

Max Range: 14.3512. Min Range: -14.3512

Max Act: 13.6468. Min Act: -0.0000

Data Index: 605834 (The Pile)

Max Activating Token Index: 738

Text #6

Max Range: 14.3512. Min Range: -14.3512

Max Act: 14.1240. Min Act: -0.0000

Data Index: 814717 (The Pile)

Max Activating Token Index: 400

Text #7

Max Range: 14.3512. Min Range: -14.3512

Max Act: 13.8184. Min Act: -0.0000

Data Index: 1049765 (The Pile)

Max Activating Token Index: 357

Text #8

Max Range: 14.3512. Min Range: -14.3512

Max Act: 13.4866. Min Act: -0.0000

Data Index: 1910748 (The Pile)

Max Activating Token Index: 692

Text #9

Max Range: 14.3512. Min Range: -14.3512

Max Act: 13.2401. Min Act: -0.0000

Data Index: 276678 (The Pile)

Max Activating Token Index: 526

Text #10

Max Range: 14.3512. Min Range: -14.3512

Max Act: 13.2159. Min Act: -0.0000

Data Index: 471157 (The Pile)

Max Activating Token Index: 399

Text #11

Max Range: 14.3512. Min Range: -14.3512

Max Act: 12.9610. Min Act: -0.0000

Data Index: 1923649 (The Pile)

Max Activating Token Index: 966

Text #12

Max Range: 14.3512. Min Range: -14.3512

Max Act: 13.2262. Min Act: -0.0000

Data Index: 1115573 (The Pile)

Max Activating Token Index: 919

Text #13

Max Range: 14.3512. Min Range: -14.3512

Max Act: 12.7737. Min Act: -0.0000

Data Index: 73759 (The Pile)

Max Activating Token Index: 158

Text #14

Max Range: 14.3512. Min Range: -14.3512

Max Act: 12.2724. Min Act: -0.0000

Data Index: 817324 (The Pile)

Max Activating Token Index: 896

Text #15

Max Range: 14.3512. Min Range: -14.3512

Max Act: 12.6619. Min Act: -0.0000

Data Index: 69641 (The Pile)

Max Activating Token Index: 88

Text #16

Max Range: 14.3512. Min Range: -14.3512

Max Act: 12.4178. Min Act: -0.0000

Data Index: 1212432 (The Pile)

Max Activating Token Index: 851

Text #17

Max Range: 14.3512. Min Range: -14.3512

Max Act: 12.2492. Min Act: -0.0000

Data Index: 1707714 (The Pile)

Max Activating Token Index: 115

Text #18

Max Range: 14.3512. Min Range: -14.3512

Max Act: 11.3913. Min Act: -0.0000

Data Index: 740504 (The Pile)

Max Activating Token Index: 584

Text #19

Max Range: 14.3512. Min Range: -14.3512

Max Act: 10.8872. Min Act: -0.0000

Data Index: 87834 (The Pile)

Max Activating Token Index: 458