Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3234 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.5351. Min Act: -0.0000

Data Index: 733554 (The Pile)

Max Activating Token Index: 315

Text #1

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4366. Min Act: -0.0000

Data Index: 1056367 (The Pile)

Max Activating Token Index: 722

Text #2

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1865398 (The Pile)

Max Activating Token Index: 470

Text #3

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.3545. Min Act: -0.0000

Data Index: 58372 (The Pile)

Max Activating Token Index: 672

Text #4

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4238. Min Act: -0.0000

Data Index: 1034287 (The Pile)

Max Activating Token Index: 693

Text #5

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4100. Min Act: -0.0000

Data Index: 227325 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.3944. Min Act: -0.0000

Data Index: 660912 (The Pile)

Max Activating Token Index: 460

Text #7

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.3306. Min Act: -0.0000

Data Index: 73996 (The Pile)

Max Activating Token Index: 590

Text #8

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.3735. Min Act: -0.0000

Data Index: 1101701 (The Pile)

Max Activating Token Index: 443

Text #9

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.3582. Min Act: -0.0000

Data Index: 1139498 (The Pile)

Max Activating Token Index: 300

Text #10

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.3783. Min Act: -0.0000

Data Index: 219637 (The Pile)

Max Activating Token Index: 107

Text #11

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.3419. Min Act: -0.0000

Data Index: 540308 (The Pile)

Max Activating Token Index: 463

Text #12

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.3611. Min Act: -0.0000

Data Index: 253510 (The Pile)

Max Activating Token Index: 115

Text #13

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.3436. Min Act: -0.0000

Data Index: 574809 (The Pile)

Max Activating Token Index: 712

Text #14

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.3493. Min Act: -0.0000

Data Index: 927989 (The Pile)

Max Activating Token Index: 256

Text #15

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.3371. Min Act: -0.0000

Data Index: 1514160 (The Pile)

Max Activating Token Index: 746

Text #16

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.3700. Min Act: -0.0000

Data Index: 963568 (The Pile)

Max Activating Token Index: 72

Text #17

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.3356. Min Act: -0.0000

Data Index: 571184 (The Pile)

Max Activating Token Index: 328

Text #18

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1305745 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.3579. Min Act: -0.0000

Data Index: 163404 (The Pile)

Max Activating Token Index: 402