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

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

Neuron 185 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0530. Min Act: -0.0006

Data Index: 334454 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0494. Min Act: -0.0006

Data Index: 79426 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0445. Min Act: -0.0006

Data Index: 1342187 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0429. Min Act: -0.0006

Data Index: 965794 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0428. Min Act: -0.0006

Data Index: 690690 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0426. Min Act: -0.0006

Data Index: 741611 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0414. Min Act: -0.0006

Data Index: 89299 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0401. Min Act: -0.0006

Data Index: 430682 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0411. Min Act: -0.0006

Data Index: 496742 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0403. Min Act: -0.0006

Data Index: 98289 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0426. Min Act: -0.0006

Data Index: 818123 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0402. Min Act: -0.0006

Data Index: 387275 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0393. Min Act: -0.0006

Data Index: 77310 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0401. Min Act: -0.0007

Data Index: 999634 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0391. Min Act: -0.0006

Data Index: 1220858 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0408. Min Act: -0.0006

Data Index: 7551 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0399. Min Act: -0.0006

Data Index: 667220 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0389. Min Act: -0.0006

Data Index: 889254 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0398. Min Act: -0.0006

Data Index: 54955 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0398. Min Act: -0.0006

Data Index: 73119 (C4 (Web Text))

Max Activating Token Index: 144