Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 174 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1228617 (The Pile)

Max Activating Token Index: 767

Text #1

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1631767 (The Pile)

Max Activating Token Index: 924

Text #2

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1631418 (The Pile)

Max Activating Token Index: 572

Text #3

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.5725. Min Act: -0.0000

Data Index: 65748 (The Pile)

Max Activating Token Index: 320

Text #4

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.5761. Min Act: -0.0000

Data Index: 854674 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.5321. Min Act: -0.0000

Data Index: 1928619 (The Pile)

Max Activating Token Index: 143

Text #6

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1477389 (The Pile)

Max Activating Token Index: 517

Text #7

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.4901. Min Act: -0.0000

Data Index: 1613285 (The Pile)

Max Activating Token Index: 861

Text #8

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.4980. Min Act: -0.0000

Data Index: 1816825 (The Pile)

Max Activating Token Index: 839

Text #9

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.5162. Min Act: -0.0000

Data Index: 147693 (The Pile)

Max Activating Token Index: 431

Text #10

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.5494. Min Act: -0.0000

Data Index: 933753 (The Pile)

Max Activating Token Index: 737

Text #11

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1706683 (The Pile)

Max Activating Token Index: 162

Text #12

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.5090. Min Act: -0.0000

Data Index: 330963 (The Pile)

Max Activating Token Index: 46

Text #13

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1491186 (The Pile)

Max Activating Token Index: 782

Text #14

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1201762 (The Pile)

Max Activating Token Index: 482

Text #15

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.4719. Min Act: -0.0000

Data Index: 556960 (The Pile)

Max Activating Token Index: 364

Text #16

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.4475. Min Act: -0.0000

Data Index: 151178 (The Pile)

Max Activating Token Index: 393

Text #17

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.4768. Min Act: -0.0000

Data Index: 260464 (The Pile)

Max Activating Token Index: 688

Text #18

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1168730 (The Pile)

Max Activating Token Index: 619

Text #19

Max Range: 0.6257. Min Range: -0.6257

Max Act: 0.4884. Min Act: -0.0000

Data Index: 922422 (The Pile)

Max Activating Token Index: 566