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

Dataset: The Pile

Neuron 988 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: 3.7599. Min Range: -3.7599

Max Act: 3.3489. Min Act: -0.0000

Data Index: 277884 (The Pile)

Max Activating Token Index: 871

Text #1

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.7599. Min Act: -0.0000

Data Index: 266465 (The Pile)

Max Activating Token Index: 283

Text #2

Max Range: 3.7599. Min Range: -3.7599

Max Act: 2.7980. Min Act: -0.0000

Data Index: 1058497 (The Pile)

Max Activating Token Index: 429

Text #3

Max Range: 3.7599. Min Range: -3.7599

Max Act: 3.3052. Min Act: -0.0000

Data Index: 1820113 (The Pile)

Max Activating Token Index: 814

Text #4

Max Range: 3.7599. Min Range: -3.7599

Max Act: 2.9890. Min Act: -0.0000

Data Index: 232144 (The Pile)

Max Activating Token Index: 816

Text #5

Max Range: 3.7599. Min Range: -3.7599

Max Act: 2.8099. Min Act: -0.0000

Data Index: 1224769 (The Pile)

Max Activating Token Index: 374

Text #6

Max Range: 3.7599. Min Range: -3.7599

Max Act: 2.8996. Min Act: -0.0000

Data Index: 834911 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 3.7599. Min Range: -3.7599

Max Act: 2.8797. Min Act: -0.0000

Data Index: 990466 (The Pile)

Max Activating Token Index: 176

Text #8

Max Range: 3.7599. Min Range: -3.7599

Max Act: 2.7438. Min Act: -0.0000

Data Index: 451867 (The Pile)

Max Activating Token Index: 840

Text #9

Max Range: 3.7599. Min Range: -3.7599

Max Act: 2.3629. Min Act: -0.0000

Data Index: 791160 (The Pile)

Max Activating Token Index: 114

Text #10

Max Range: 3.7599. Min Range: -3.7599

Max Act: 2.4007. Min Act: -0.0000

Data Index: 98677 (The Pile)

Max Activating Token Index: 745

Text #11

Max Range: 3.7599. Min Range: -3.7599

Max Act: 2.8265. Min Act: -0.0000

Data Index: 1749852 (The Pile)

Max Activating Token Index: 380

Text #12

Max Range: 3.7599. Min Range: -3.7599

Max Act: 2.5742. Min Act: -0.0000

Data Index: 1732726 (The Pile)

Max Activating Token Index: 590

Text #13

Max Range: 3.7599. Min Range: -3.7599

Max Act: 2.5360. Min Act: -0.0000

Data Index: 1670386 (The Pile)

Max Activating Token Index: 392

Text #14

Max Range: 3.7599. Min Range: -3.7599

Max Act: 2.1300. Min Act: -0.0000

Data Index: 1206815 (The Pile)

Max Activating Token Index: 464

Text #15

Max Range: 3.7599. Min Range: -3.7599

Max Act: 2.4623. Min Act: -0.0000

Data Index: 1872439 (The Pile)

Max Activating Token Index: 537

Text #16

Max Range: 3.7599. Min Range: -3.7599

Max Act: 2.5680. Min Act: -0.0000

Data Index: 556701 (The Pile)

Max Activating Token Index: 469

Text #17

Max Range: 3.7599. Min Range: -3.7599

Max Act: 2.2083. Min Act: -0.0000

Data Index: 294116 (The Pile)

Max Activating Token Index: 346

Text #18

Max Range: 3.7599. Min Range: -3.7599

Max Act: 2.5272. Min Act: -0.0000

Data Index: 1410516 (The Pile)

Max Activating Token Index: 691

Text #19

Max Range: 3.7599. Min Range: -3.7599

Max Act: 2.1312. Min Act: -0.0000

Data Index: 1817477 (The Pile)

Max Activating Token Index: 745