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

Dataset: The Pile

Neuron 2725 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2962. Min Range: -3.2962

Max Act: 3.2962. Min Act: -0.0000

Data Index: 108990 (The Pile)

Max Activating Token Index: 23

Text #1

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.9743. Min Act: -0.0000

Data Index: 576581 (The Pile)

Max Activating Token Index: 223

Text #2

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.9085. Min Act: -0.0000

Data Index: 684609 (The Pile)

Max Activating Token Index: 449

Text #3

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.7189. Min Act: -0.0000

Data Index: 958255 (The Pile)

Max Activating Token Index: 501

Text #4

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.7553. Min Act: -0.0000

Data Index: 707681 (The Pile)

Max Activating Token Index: 981

Text #5

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.6872. Min Act: -0.0000

Data Index: 1992633 (The Pile)

Max Activating Token Index: 17

Text #6

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.8002. Min Act: -0.0000

Data Index: 1925298 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.7659. Min Act: -0.0000

Data Index: 1036456 (The Pile)

Max Activating Token Index: 565

Text #8

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.7626. Min Act: -0.0000

Data Index: 1554195 (The Pile)

Max Activating Token Index: 790

Text #9

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.6220. Min Act: -0.0000

Data Index: 690277 (The Pile)

Max Activating Token Index: 20

Text #10

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.6119. Min Act: -0.0000

Data Index: 436072 (The Pile)

Max Activating Token Index: 26

Text #11

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.7316. Min Act: -0.0000

Data Index: 1166477 (The Pile)

Max Activating Token Index: 26

Text #12

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.5685. Min Act: -0.0000

Data Index: 1157043 (The Pile)

Max Activating Token Index: 430

Text #13

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.6841. Min Act: -0.0000

Data Index: 1437676 (The Pile)

Max Activating Token Index: 23

Text #14

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.5559. Min Act: -0.0000

Data Index: 410231 (The Pile)

Max Activating Token Index: 380

Text #15

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.4048. Min Act: -0.0001

Data Index: 280000 (The Pile)

Max Activating Token Index: 773

Text #16

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.4144. Min Act: -0.0000

Data Index: 1556120 (The Pile)

Max Activating Token Index: 232

Text #17

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.3557. Min Act: -0.0000

Data Index: 1807885 (The Pile)

Max Activating Token Index: 382

Text #18

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.3336. Min Act: -0.0000

Data Index: 913634 (The Pile)

Max Activating Token Index: 39

Text #19

Max Range: 3.2962. Min Range: -3.2962

Max Act: 2.4462. Min Act: -0.0001

Data Index: 1789045 (The Pile)

Max Activating Token Index: 438