Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5860 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.4566. Min Act: -0.0000

Data Index: 114589 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3091. Min Act: -0.0000

Data Index: 223697 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3252. Min Act: -0.0000

Data Index: 1082953 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3242. Min Act: -0.0000

Data Index: 838887 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2951. Min Act: -0.0000

Data Index: 613200 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1011422 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2671. Min Act: -0.0000

Data Index: 1037556 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2628. Min Act: -0.0000

Data Index: 616339 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1327942 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2707. Min Act: -0.0000

Data Index: 671073 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2579. Min Act: -0.0000

Data Index: 619415 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1228599 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2565. Min Act: 0.0001

Data Index: 1204562 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2507. Min Act: 0.0000

Data Index: 201307 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1269828 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1069715 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2325. Min Act: -0.0000

Data Index: 663620 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2284. Min Act: -0.0000

Data Index: 44590 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2316. Min Act: 0.0000

Data Index: 757111 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1049814 (C4 (Web Text))

Max Activating Token Index: 594