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

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

Neuron 3120 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0551. Min Act: -0.0002

Data Index: 528520 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1037285 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0568. Min Act: -0.0001

Data Index: 361861 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1286412 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0529. Min Act: -0.0001

Data Index: 1649789 (Python Code)

Max Activating Token Index: 112

Text #5

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1583893 (Python Code)

Max Activating Token Index: 207

Text #6

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0547. Min Act: -0.0001

Data Index: 1229664 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1364726 (Python Code)

Max Activating Token Index: 252

Text #8

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0518. Min Act: -0.0001

Data Index: 5279 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1344494 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0502. Min Act: -0.0002

Data Index: 437108 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0487. Min Act: -0.0002

Data Index: 696306 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0500. Min Act: -0.0001

Data Index: 1162825 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0496. Min Act: -0.0001

Data Index: 1423368 (Python Code)

Max Activating Token Index: 144

Text #14

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0483. Min Act: -0.0001

Data Index: 1620172 (Python Code)

Max Activating Token Index: 13

Text #15

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0456. Min Act: -0.0001

Data Index: 730133 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0472. Min Act: -0.0001

Data Index: 1432043 (Python Code)

Max Activating Token Index: 620

Text #17

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0479. Min Act: -0.0001

Data Index: 1385557 (Python Code)

Max Activating Token Index: 384

Text #18

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1472792 (Python Code)

Max Activating Token Index: 255

Text #19

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0455. Min Act: -0.0002

Data Index: 786775 (C4 (Web Text))

Max Activating Token Index: 700