Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1506 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0642. Min Act: -0.0005

Data Index: 112466 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0558. Min Act: -0.0005

Data Index: 595494 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0551. Min Act: -0.0005

Data Index: 297229 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0513. Min Act: -0.0005

Data Index: 595354 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0529. Min Act: -0.0005

Data Index: 754472 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0484. Min Act: -0.0005

Data Index: 35355 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0501. Min Act: -0.0005

Data Index: 668231 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0514. Min Act: -0.0005

Data Index: 297307 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0495. Min Act: -0.0005

Data Index: 977669 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0480. Min Act: -0.0005

Data Index: 110161 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0490. Min Act: -0.0005

Data Index: 369147 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0489. Min Act: -0.0005

Data Index: 908439 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0503. Min Act: -0.0005

Data Index: 958138 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0453. Min Act: -0.0005

Data Index: 67545 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0439. Min Act: -0.0005

Data Index: 226848 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0440. Min Act: -0.0005

Data Index: 256262 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0460. Min Act: -0.0005

Data Index: 539769 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0436. Min Act: -0.0005

Data Index: 224612 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0457. Min Act: -0.0005

Data Index: 319558 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0460. Min Act: -0.0005

Data Index: 294574 (C4 (Web Text))

Max Activating Token Index: 865