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

Dataset: The Pile

Neuron 3530 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: 0.3295. Min Range: -0.3295

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1586564 (The Pile)

Max Activating Token Index: 576

Text #1

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1571100 (The Pile)

Max Activating Token Index: 231

Text #2

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.3128. Min Act: -0.0000

Data Index: 116281 (The Pile)

Max Activating Token Index: 239

Text #3

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2912. Min Act: -0.0000

Data Index: 1229644 (The Pile)

Max Activating Token Index: 158

Text #4

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.3076. Min Act: -0.0000

Data Index: 1147690 (The Pile)

Max Activating Token Index: 487

Text #5

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2798. Min Act: -0.0000

Data Index: 638701 (The Pile)

Max Activating Token Index: 568

Text #6

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2972. Min Act: -0.0000

Data Index: 714313 (The Pile)

Max Activating Token Index: 122

Text #7

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2852. Min Act: -0.0000

Data Index: 26886 (The Pile)

Max Activating Token Index: 228

Text #8

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2817. Min Act: -0.0000

Data Index: 823075 (The Pile)

Max Activating Token Index: 153

Text #9

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2746. Min Act: -0.0000

Data Index: 515286 (The Pile)

Max Activating Token Index: 639

Text #10

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.1769. Min Act: -0.0000

Data Index: 1338231 (The Pile)

Max Activating Token Index: 620

Text #11

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2655. Min Act: -0.0000

Data Index: 1102519 (The Pile)

Max Activating Token Index: 33

Text #12

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2951. Min Act: -0.0000

Data Index: 11780 (The Pile)

Max Activating Token Index: 346

Text #13

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1378245 (The Pile)

Max Activating Token Index: 445

Text #14

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1896942 (The Pile)

Max Activating Token Index: 654

Text #15

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2447. Min Act: -0.0000

Data Index: 1554730 (The Pile)

Max Activating Token Index: 671

Text #16

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2698. Min Act: -0.0000

Data Index: 977052 (The Pile)

Max Activating Token Index: 892

Text #17

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2674. Min Act: -0.0000

Data Index: 1582364 (The Pile)

Max Activating Token Index: 351

Text #18

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2759. Min Act: -0.0000

Data Index: 1462823 (The Pile)

Max Activating Token Index: 302

Text #19

Max Range: 0.3295. Min Range: -0.3295

Max Act: 0.2404. Min Act: -0.0000

Data Index: 422052 (The Pile)

Max Activating Token Index: 552