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

Dataset: The Pile

Neuron 812 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.9186. Min Act: -0.0000

Data Index: 940250 (The Pile)

Max Activating Token Index: 382

Text #1

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.9033. Min Act: -0.0000

Data Index: 547259 (The Pile)

Max Activating Token Index: 849

Text #2

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1116882 (The Pile)

Max Activating Token Index: 493

Text #3

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1615043 (The Pile)

Max Activating Token Index: 495

Text #4

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1478987 (The Pile)

Max Activating Token Index: 896

Text #5

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1563203 (The Pile)

Max Activating Token Index: 688

Text #6

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6154. Min Act: -0.0000

Data Index: 426447 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.5789. Min Act: -0.0000

Data Index: 614239 (The Pile)

Max Activating Token Index: 787

Text #8

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.5787. Min Act: -0.0000

Data Index: 594193 (The Pile)

Max Activating Token Index: 276

Text #9

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1473072 (The Pile)

Max Activating Token Index: 330

Text #10

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.5237. Min Act: -0.0000

Data Index: 737935 (The Pile)

Max Activating Token Index: 782

Text #11

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.5053. Min Act: -0.0000

Data Index: 920695 (The Pile)

Max Activating Token Index: 620

Text #12

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1467535 (The Pile)

Max Activating Token Index: 232

Text #13

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.4315. Min Act: -0.0000

Data Index: 855137 (The Pile)

Max Activating Token Index: 280

Text #14

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.4867. Min Act: -0.0000

Data Index: 288687 (The Pile)

Max Activating Token Index: 626

Text #15

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.4605. Min Act: -0.0000

Data Index: 1055364 (The Pile)

Max Activating Token Index: 422

Text #16

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.4043. Min Act: -0.0000

Data Index: 1974445 (The Pile)

Max Activating Token Index: 694

Text #17

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.4433. Min Act: -0.0000

Data Index: 481695 (The Pile)

Max Activating Token Index: 860

Text #18

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1379774 (The Pile)

Max Activating Token Index: 559

Text #19

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.3639. Min Act: -0.0000

Data Index: 541976 (The Pile)

Max Activating Token Index: 745