Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1670 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0508. Min Act: -0.0006

Data Index: 117183 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0496. Min Act: -0.0006

Data Index: 88638 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0493. Min Act: -0.0006

Data Index: 123449 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0503. Min Act: -0.0006

Data Index: 295599 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0477. Min Act: -0.0006

Data Index: 1322280 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0471. Min Act: -0.0006

Data Index: 506658 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0466. Min Act: -0.0006

Data Index: 900460 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0479. Min Act: -0.0006

Data Index: 573963 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0481. Min Act: -0.0006

Data Index: 159325 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0462. Min Act: -0.0006

Data Index: 278040 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0451. Min Act: -0.0006

Data Index: 37662 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0486. Min Act: -0.0006

Data Index: 205834 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0455. Min Act: -0.0006

Data Index: 716401 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0485. Min Act: -0.0006

Data Index: 1213711 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0462. Min Act: -0.0006

Data Index: 9897 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0425. Min Act: -0.0006

Data Index: 678823 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0450. Min Act: -0.0006

Data Index: 1277691 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0423. Min Act: -0.0006

Data Index: 346527 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0422. Min Act: -0.0006

Data Index: 750778 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0447. Min Act: -0.0006

Data Index: 637875 (C4 (Web Text))

Max Activating Token Index: 857