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

Dataset: The Pile

Neuron 1272 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: 0.5879. Min Range: -0.5879

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1164571 (The Pile)

Max Activating Token Index: 369

Text #1

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1783232 (The Pile)

Max Activating Token Index: 156

Text #2

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1843526 (The Pile)

Max Activating Token Index: 624

Text #3

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5264. Min Act: -0.0000

Data Index: 115288 (The Pile)

Max Activating Token Index: 573

Text #4

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4807. Min Act: -0.0000

Data Index: 729408 (The Pile)

Max Activating Token Index: 908

Text #5

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4997. Min Act: -0.0000

Data Index: 716394 (The Pile)

Max Activating Token Index: 219

Text #6

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1890515 (The Pile)

Max Activating Token Index: 420

Text #7

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4557. Min Act: -0.0000

Data Index: 841165 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4590. Min Act: -0.0000

Data Index: 1925163 (The Pile)

Max Activating Token Index: 229

Text #9

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4722. Min Act: -0.0000

Data Index: 1065045 (The Pile)

Max Activating Token Index: 488

Text #10

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4535. Min Act: -0.0000

Data Index: 771277 (The Pile)

Max Activating Token Index: 490

Text #11

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1849972 (The Pile)

Max Activating Token Index: 839

Text #12

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4303. Min Act: -0.0000

Data Index: 1551895 (The Pile)

Max Activating Token Index: 372

Text #13

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1363501 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4112. Min Act: -0.0000

Data Index: 7843 (The Pile)

Max Activating Token Index: 359

Text #15

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4670. Min Act: -0.0000

Data Index: 114259 (The Pile)

Max Activating Token Index: 460

Text #16

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1562886 (The Pile)

Max Activating Token Index: 399

Text #17

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1886410 (The Pile)

Max Activating Token Index: 555

Text #18

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4130. Min Act: -0.0000

Data Index: 149748 (The Pile)

Max Activating Token Index: 471

Text #19

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4381. Min Act: -0.0000

Data Index: 76167 (The Pile)

Max Activating Token Index: 455