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

Dataset: The Pile

Neuron 2663 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.5089. Min Act: -0.0000

Data Index: 1282480 (The Pile)

Max Activating Token Index: 299

Text #1

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.3744. Min Act: -0.0000

Data Index: 1034662 (The Pile)

Max Activating Token Index: 888

Text #2

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.2732. Min Act: -0.0000

Data Index: 1377007 (The Pile)

Max Activating Token Index: 997

Text #3

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.2783. Min Act: -0.0000

Data Index: 885457 (The Pile)

Max Activating Token Index: 476

Text #4

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.2456. Min Act: -0.0000

Data Index: 1358469 (The Pile)

Max Activating Token Index: 805

Text #5

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.2066. Min Act: -0.0000

Data Index: 919595 (The Pile)

Max Activating Token Index: 603

Text #6

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.1216. Min Act: -0.0000

Data Index: 1983822 (The Pile)

Max Activating Token Index: 644

Text #7

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.3289. Min Act: -0.0000

Data Index: 564037 (The Pile)

Max Activating Token Index: 675

Text #8

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.2527. Min Act: -0.0000

Data Index: 1299050 (The Pile)

Max Activating Token Index: 512

Text #9

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.2402. Min Act: -0.0000

Data Index: 1761674 (The Pile)

Max Activating Token Index: 568

Text #10

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.2068. Min Act: -0.0000

Data Index: 1623542 (The Pile)

Max Activating Token Index: 437

Text #11

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.1425. Min Act: -0.0000

Data Index: 781167 (The Pile)

Max Activating Token Index: 987

Text #12

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.2039. Min Act: -0.0000

Data Index: 676088 (The Pile)

Max Activating Token Index: 328

Text #13

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1420068 (The Pile)

Max Activating Token Index: 875

Text #14

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.1298. Min Act: -0.0000

Data Index: 1359497 (The Pile)

Max Activating Token Index: 857

Text #15

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.1172. Min Act: -0.0000

Data Index: 454004 (The Pile)

Max Activating Token Index: 993

Text #16

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.0967. Min Act: -0.0000

Data Index: 1136693 (The Pile)

Max Activating Token Index: 297

Text #17

Max Range: 1.5089. Min Range: -1.5089

Max Act: 0.9682. Min Act: -0.0000

Data Index: 1971870 (The Pile)

Max Activating Token Index: 568

Text #18

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.1544. Min Act: -0.0000

Data Index: 1194354 (The Pile)

Max Activating Token Index: 551

Text #19

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.0682. Min Act: -0.0000

Data Index: 445477 (The Pile)

Max Activating Token Index: 660