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

Dataset: The Pile

Neuron 4536 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: 1.7068. Min Range: -1.7068

Max Act: 1.7068. Min Act: -0.0000

Data Index: 344018 (The Pile)

Max Activating Token Index: 416

Text #1

Max Range: 1.7068. Min Range: -1.7068

Max Act: 1.4320. Min Act: -0.0000

Data Index: 1028961 (The Pile)

Max Activating Token Index: 835

Text #2

Max Range: 1.7068. Min Range: -1.7068

Max Act: 1.3259. Min Act: -0.0000

Data Index: 1978942 (The Pile)

Max Activating Token Index: 849

Text #3

Max Range: 1.7068. Min Range: -1.7068

Max Act: 1.4687. Min Act: -0.0000

Data Index: 1679677 (The Pile)

Max Activating Token Index: 593

Text #4

Max Range: 1.7068. Min Range: -1.7068

Max Act: 1.4876. Min Act: -0.0000

Data Index: 1298863 (The Pile)

Max Activating Token Index: 292

Text #5

Max Range: 1.7068. Min Range: -1.7068

Max Act: 1.4625. Min Act: -0.0000

Data Index: 1409335 (The Pile)

Max Activating Token Index: 327

Text #6

Max Range: 1.7068. Min Range: -1.7068

Max Act: 1.4308. Min Act: -0.0000

Data Index: 1581329 (The Pile)

Max Activating Token Index: 33

Text #7

Max Range: 1.7068. Min Range: -1.7068

Max Act: 1.5243. Min Act: -0.0000

Data Index: 284255 (The Pile)

Max Activating Token Index: 423

Text #8

Max Range: 1.7068. Min Range: -1.7068

Max Act: 1.5795. Min Act: -0.0000

Data Index: 859611 (The Pile)

Max Activating Token Index: 480

Text #9

Max Range: 1.7068. Min Range: -1.7068

Max Act: 1.5112. Min Act: -0.0000

Data Index: 1551121 (The Pile)

Max Activating Token Index: 368

Text #10

Max Range: 1.7068. Min Range: -1.7068

Max Act: 1.5936. Min Act: -0.0000

Data Index: 1471323 (The Pile)

Max Activating Token Index: 189

Text #11

Max Range: 1.7068. Min Range: -1.7068

Max Act: 1.4126. Min Act: -0.0000

Data Index: 498308 (The Pile)

Max Activating Token Index: 907

Text #12

Max Range: 1.7068. Min Range: -1.7068

Max Act: 1.3288. Min Act: -0.0000

Data Index: 1239524 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 1.7068. Min Range: -1.7068

Max Act: 1.3007. Min Act: -0.0000

Data Index: 840630 (The Pile)

Max Activating Token Index: 617

Text #14

Max Range: 1.7068. Min Range: -1.7068

Max Act: 1.2816. Min Act: -0.0000

Data Index: 1655032 (The Pile)

Max Activating Token Index: 289

Text #15

Max Range: 1.7068. Min Range: -1.7068

Max Act: 1.3903. Min Act: -0.0000

Data Index: 665690 (The Pile)

Max Activating Token Index: 1004

Text #16

Max Range: 1.7068. Min Range: -1.7068

Max Act: 1.3900. Min Act: -0.0000

Data Index: 1922161 (The Pile)

Max Activating Token Index: 724

Text #17

Max Range: 1.7068. Min Range: -1.7068

Max Act: 1.3226. Min Act: -0.0000

Data Index: 1467906 (The Pile)

Max Activating Token Index: 807

Text #18

Max Range: 1.7068. Min Range: -1.7068

Max Act: 1.2651. Min Act: -0.0000

Data Index: 979541 (The Pile)

Max Activating Token Index: 220

Text #19

Max Range: 1.7068. Min Range: -1.7068

Max Act: 1.3003. Min Act: -0.0000

Data Index: 1543025 (The Pile)

Max Activating Token Index: 434