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

Dataset: The Pile

Neuron 3882 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: 1.2275. Min Range: -1.2275

Max Act: 1.2275. Min Act: -0.0000

Data Index: 1056851 (The Pile)

Max Activating Token Index: 504

Text #1

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0094. Min Act: -0.0000

Data Index: 421480 (The Pile)

Max Activating Token Index: 1006

Text #2

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0238. Min Act: -0.0000

Data Index: 641515 (The Pile)

Max Activating Token Index: 466

Text #3

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0336. Min Act: -0.0000

Data Index: 910074 (The Pile)

Max Activating Token Index: 473

Text #4

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9665. Min Act: -0.0000

Data Index: 22899 (The Pile)

Max Activating Token Index: 525

Text #5

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9513. Min Act: -0.0000

Data Index: 374059 (The Pile)

Max Activating Token Index: 756

Text #6

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9009. Min Act: -0.0000

Data Index: 225816 (The Pile)

Max Activating Token Index: 340

Text #7

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9187. Min Act: -0.0000

Data Index: 1198332 (The Pile)

Max Activating Token Index: 255

Text #8

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1093568 (The Pile)

Max Activating Token Index: 901

Text #9

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.8850. Min Act: -0.0000

Data Index: 187878 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.8551. Min Act: -0.0000

Data Index: 301575 (The Pile)

Max Activating Token Index: 369

Text #11

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1817164 (The Pile)

Max Activating Token Index: 93

Text #12

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1356049 (The Pile)

Max Activating Token Index: 654

Text #13

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.8329. Min Act: -0.0000

Data Index: 463247 (The Pile)

Max Activating Token Index: 247

Text #14

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.7842. Min Act: -0.0000

Data Index: 1101966 (The Pile)

Max Activating Token Index: 778

Text #15

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.8055. Min Act: -0.0000

Data Index: 1687618 (The Pile)

Max Activating Token Index: 242

Text #16

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.8342. Min Act: -0.0000

Data Index: 1455055 (The Pile)

Max Activating Token Index: 499

Text #17

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.7988. Min Act: -0.0000

Data Index: 1065906 (The Pile)

Max Activating Token Index: 654

Text #18

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.7897. Min Act: -0.0000

Data Index: 1120810 (The Pile)

Max Activating Token Index: 144

Text #19

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.7781. Min Act: -0.0000

Data Index: 438573 (The Pile)

Max Activating Token Index: 686