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

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

Neuron 921 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: 0.0518. Min Range: -0.0518

Max Act: 0.0517. Min Act: -0.0006

Data Index: 174546 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0517. Min Act: -0.0006

Data Index: 313045 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0515. Min Act: -0.0006

Data Index: 606462 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0518. Min Act: -0.0006

Data Index: 439129 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0514. Min Act: -0.0006

Data Index: 1148071 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0499. Min Act: -0.0005

Data Index: 1286792 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0495. Min Act: -0.0006

Data Index: 340534 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0506. Min Act: -0.0006

Data Index: 918446 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0487. Min Act: -0.0006

Data Index: 593698 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0466. Min Act: -0.0006

Data Index: 650189 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0478. Min Act: -0.0006

Data Index: 701131 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0475. Min Act: -0.0006

Data Index: 1274628 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0475. Min Act: -0.0006

Data Index: 1285707 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0470. Min Act: -0.0006

Data Index: 601025 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0479. Min Act: -0.0006

Data Index: 774098 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0467. Min Act: -0.0006

Data Index: 602338 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0448. Min Act: -0.0006

Data Index: 527581 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0465. Min Act: -0.0006

Data Index: 691158 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0472. Min Act: -0.0006

Data Index: 1352559 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0451. Min Act: -0.0006

Data Index: 591008 (C4 (Web Text))

Max Activating Token Index: 602