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

Dataset: The Pile

Neuron 1170 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: 0.9382. Min Range: -0.9382

Max Act: 0.9136. Min Act: -0.0000

Data Index: 1902563 (The Pile)

Max Activating Token Index: 220

Text #1

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.9348. Min Act: -0.0000

Data Index: 641214 (The Pile)

Max Activating Token Index: 489

Text #2

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.9382. Min Act: -0.0000

Data Index: 1598356 (The Pile)

Max Activating Token Index: 248

Text #3

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.8871. Min Act: -0.0000

Data Index: 1866372 (The Pile)

Max Activating Token Index: 15

Text #4

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.8570. Min Act: -0.0000

Data Index: 515868 (The Pile)

Max Activating Token Index: 735

Text #5

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.8080. Min Act: -0.0000

Data Index: 420058 (The Pile)

Max Activating Token Index: 998

Text #6

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1075032 (The Pile)

Max Activating Token Index: 238

Text #7

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7913. Min Act: -0.0000

Data Index: 1371145 (The Pile)

Max Activating Token Index: 45

Text #8

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1208401 (The Pile)

Max Activating Token Index: 691

Text #9

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1717305 (The Pile)

Max Activating Token Index: 835

Text #10

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7632. Min Act: -0.0000

Data Index: 624591 (The Pile)

Max Activating Token Index: 352

Text #11

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7466. Min Act: -0.0000

Data Index: 340172 (The Pile)

Max Activating Token Index: 751

Text #12

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7520. Min Act: -0.0000

Data Index: 1271978 (The Pile)

Max Activating Token Index: 461

Text #13

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1002600 (The Pile)

Max Activating Token Index: 15

Text #14

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7513. Min Act: -0.0000

Data Index: 678098 (The Pile)

Max Activating Token Index: 416

Text #15

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1356121 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7091. Min Act: -0.0000

Data Index: 650102 (The Pile)

Max Activating Token Index: 142

Text #17

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7489. Min Act: -0.0000

Data Index: 332488 (The Pile)

Max Activating Token Index: 541

Text #18

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1304381 (The Pile)

Max Activating Token Index: 592

Text #19

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1486562 (The Pile)

Max Activating Token Index: 218