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

Dataset: The Pile

Neuron 684 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3536. Min Act: 0.0000

Data Index: 27734 (The Pile)

Max Activating Token Index: 120

Text #1

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3063. Min Act: 0.0000

Data Index: 518189 (The Pile)

Max Activating Token Index: 99

Text #2

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2868. Min Act: 0.0001

Data Index: 1078272 (The Pile)

Max Activating Token Index: 84

Text #3

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2711. Min Act: -0.0000

Data Index: 493255 (The Pile)

Max Activating Token Index: 651

Text #4

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2647. Min Act: -0.0000

Data Index: 775323 (The Pile)

Max Activating Token Index: 296

Text #5

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2535. Min Act: 0.0000

Data Index: 85659 (The Pile)

Max Activating Token Index: 673

Text #6

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1399768 (The Pile)

Max Activating Token Index: 745

Text #7

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2465. Min Act: -0.0000

Data Index: 232694 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1388873 (The Pile)

Max Activating Token Index: 979

Text #9

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2300. Min Act: 0.0001

Data Index: 983882 (The Pile)

Max Activating Token Index: 661

Text #10

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2270. Min Act: 0.0000

Data Index: 266958 (The Pile)

Max Activating Token Index: 120

Text #11

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2167. Min Act: 0.0000

Data Index: 493595 (The Pile)

Max Activating Token Index: 180

Text #12

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2155. Min Act: 0.0000

Data Index: 1863647 (The Pile)

Max Activating Token Index: 972

Text #13

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2090. Min Act: 0.0000

Data Index: 706983 (The Pile)

Max Activating Token Index: 610

Text #14

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2114. Min Act: 0.0001

Data Index: 1550617 (The Pile)

Max Activating Token Index: 84

Text #15

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2070. Min Act: -0.0000

Data Index: 454076 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1581475 (The Pile)

Max Activating Token Index: 538

Text #17

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.1912. Min Act: -0.0000

Data Index: 1393626 (The Pile)

Max Activating Token Index: 1011

Text #18

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.1903. Min Act: 0.0001

Data Index: 1833997 (The Pile)

Max Activating Token Index: 660

Text #19

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.1845. Min Act: -0.0000

Data Index: 1471632 (The Pile)

Max Activating Token Index: 718