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

Dataset: The Pile

Neuron 4530 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: 1.4512. Min Range: -1.4512

Max Act: 1.4512. Min Act: -0.0000

Data Index: 708163 (The Pile)

Max Activating Token Index: 915

Text #1

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.3963. Min Act: -0.0000

Data Index: 1002048 (The Pile)

Max Activating Token Index: 1004

Text #2

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.3820. Min Act: -0.0000

Data Index: 145207 (The Pile)

Max Activating Token Index: 613

Text #3

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.2449. Min Act: -0.0000

Data Index: 1356032 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.2029. Min Act: -0.0000

Data Index: 938642 (The Pile)

Max Activating Token Index: 845

Text #5

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.1124. Min Act: -0.0000

Data Index: 698231 (The Pile)

Max Activating Token Index: 974

Text #6

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.2307. Min Act: -0.0000

Data Index: 159131 (The Pile)

Max Activating Token Index: 913

Text #7

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.0945. Min Act: -0.0000

Data Index: 411939 (The Pile)

Max Activating Token Index: 1018

Text #8

Max Range: 1.4512. Min Range: -1.4512

Max Act: 0.9752. Min Act: -0.0000

Data Index: 1820943 (The Pile)

Max Activating Token Index: 580

Text #9

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.0628. Min Act: -0.0000

Data Index: 1088984 (The Pile)

Max Activating Token Index: 1018

Text #10

Max Range: 1.4512. Min Range: -1.4512

Max Act: 0.9315. Min Act: -0.0000

Data Index: 117520 (The Pile)

Max Activating Token Index: 767

Text #11

Max Range: 1.4512. Min Range: -1.4512

Max Act: 0.9882. Min Act: -0.0000

Data Index: 1465267 (The Pile)

Max Activating Token Index: 306

Text #12

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.0859. Min Act: -0.0000

Data Index: 1946528 (The Pile)

Max Activating Token Index: 104

Text #13

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.0259. Min Act: -0.0000

Data Index: 597216 (The Pile)

Max Activating Token Index: 1007

Text #14

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.0563. Min Act: -0.0000

Data Index: 291142 (The Pile)

Max Activating Token Index: 309

Text #15

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.1329. Min Act: -0.0000

Data Index: 1316667 (The Pile)

Max Activating Token Index: 885

Text #16

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.0098. Min Act: -0.0000

Data Index: 1715779 (The Pile)

Max Activating Token Index: 761

Text #17

Max Range: 1.4512. Min Range: -1.4512

Max Act: 1.0637. Min Act: -0.0000

Data Index: 1959037 (The Pile)

Max Activating Token Index: 454

Text #18

Max Range: 1.4512. Min Range: -1.4512

Max Act: 0.9608. Min Act: -0.0000

Data Index: 599506 (The Pile)

Max Activating Token Index: 633

Text #19

Max Range: 1.4512. Min Range: -1.4512

Max Act: 0.9700. Min Act: -0.0000

Data Index: 475880 (The Pile)

Max Activating Token Index: 886