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

Dataset: The Pile

Neuron 2968 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.5013. Min Act: -0.0000

Data Index: 979890 (The Pile)

Max Activating Token Index: 478

Text #1

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1139873 (The Pile)

Max Activating Token Index: 440

Text #2

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.5072. Min Act: -0.0000

Data Index: 1637124 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4494. Min Act: -0.0000

Data Index: 843542 (The Pile)

Max Activating Token Index: 433

Text #4

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4696. Min Act: -0.0000

Data Index: 700648 (The Pile)

Max Activating Token Index: 198

Text #5

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4445. Min Act: -0.0000

Data Index: 1352657 (The Pile)

Max Activating Token Index: 179

Text #6

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4576. Min Act: -0.0000

Data Index: 569227 (The Pile)

Max Activating Token Index: 81

Text #7

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4708. Min Act: -0.0001

Data Index: 1792202 (The Pile)

Max Activating Token Index: 385

Text #8

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4272. Min Act: -0.0000

Data Index: 1150373 (The Pile)

Max Activating Token Index: 248

Text #9

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1437977 (The Pile)

Max Activating Token Index: 328

Text #10

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1306533 (The Pile)

Max Activating Token Index: 110

Text #11

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1411526 (The Pile)

Max Activating Token Index: 127

Text #12

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4491. Min Act: -0.0000

Data Index: 467347 (The Pile)

Max Activating Token Index: 396

Text #13

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1364635 (The Pile)

Max Activating Token Index: 302

Text #14

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1800628 (The Pile)

Max Activating Token Index: 722

Text #15

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4088. Min Act: -0.0000

Data Index: 1811407 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3925. Min Act: -0.0000

Data Index: 80242 (The Pile)

Max Activating Token Index: 127

Text #17

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4100. Min Act: -0.0000

Data Index: 365034 (The Pile)

Max Activating Token Index: 143

Text #18

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1296939 (The Pile)

Max Activating Token Index: 911

Text #19

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4111. Min Act: -0.0001

Data Index: 427887 (The Pile)

Max Activating Token Index: 308