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

Dataset: The Pile

Neuron 1347 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: 1.6362. Min Range: -1.6362

Max Act: 1.5405. Min Act: -0.0000

Data Index: 1646417 (The Pile)

Max Activating Token Index: 482

Text #1

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.6362. Min Act: -0.0000

Data Index: 1375029 (The Pile)

Max Activating Token Index: 136

Text #2

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5479. Min Act: -0.0000

Data Index: 236488 (The Pile)

Max Activating Token Index: 205

Text #3

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4921. Min Act: -0.0000

Data Index: 132169 (The Pile)

Max Activating Token Index: 405

Text #4

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5007. Min Act: -0.0000

Data Index: 393472 (The Pile)

Max Activating Token Index: 625

Text #5

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5454. Min Act: -0.0000

Data Index: 1415307 (The Pile)

Max Activating Token Index: 646

Text #6

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4445. Min Act: -0.0000

Data Index: 1150503 (The Pile)

Max Activating Token Index: 361

Text #7

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5136. Min Act: -0.0000

Data Index: 851434 (The Pile)

Max Activating Token Index: 422

Text #8

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4274. Min Act: -0.0000

Data Index: 738040 (The Pile)

Max Activating Token Index: 372

Text #9

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.3935. Min Act: -0.0000

Data Index: 1011268 (The Pile)

Max Activating Token Index: 430

Text #10

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4008. Min Act: -0.0000

Data Index: 119784 (The Pile)

Max Activating Token Index: 307

Text #11

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4759. Min Act: -0.0000

Data Index: 1166493 (The Pile)

Max Activating Token Index: 892

Text #12

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4303. Min Act: -0.0000

Data Index: 461493 (The Pile)

Max Activating Token Index: 109

Text #13

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4278. Min Act: -0.0000

Data Index: 1866246 (The Pile)

Max Activating Token Index: 551

Text #14

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4956. Min Act: -0.0000

Data Index: 46615 (The Pile)

Max Activating Token Index: 771

Text #15

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4758. Min Act: -0.0000

Data Index: 391782 (The Pile)

Max Activating Token Index: 836

Text #16

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.5404. Min Act: -0.0000

Data Index: 282528 (The Pile)

Max Activating Token Index: 832

Text #17

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.3744. Min Act: -0.0000

Data Index: 303784 (The Pile)

Max Activating Token Index: 88

Text #18

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.3482. Min Act: -0.0000

Data Index: 1682598 (The Pile)

Max Activating Token Index: 588

Text #19

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.2087. Min Act: -0.0000

Data Index: 1613735 (The Pile)

Max Activating Token Index: 538