Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5101 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.5718. Min Act: -0.0000

Data Index: 1019826 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.5209. Min Act: -0.0000

Data Index: 922683 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.4374. Min Act: -0.0000

Data Index: 1230653 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.4300. Min Act: -0.0000

Data Index: 594616 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.3369. Min Act: -0.0000

Data Index: 1324645 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.4521. Min Act: -0.0000

Data Index: 1245583 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.3706. Min Act: -0.0000

Data Index: 1544275 (Python Code)

Max Activating Token Index: 911

Text #7

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.3637. Min Act: -0.0000

Data Index: 891853 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.3143. Min Act: -0.0000

Data Index: 783574 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.3606. Min Act: -0.0000

Data Index: 788525 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.2297. Min Act: -0.0000

Data Index: 1079731 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.2930. Min Act: -0.0000

Data Index: 610115 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.2878. Min Act: -0.0000

Data Index: 546907 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.2890. Min Act: -0.0000

Data Index: 1416173 (Python Code)

Max Activating Token Index: 947

Text #14

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.2688. Min Act: -0.0000

Data Index: 958762 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.3105. Min Act: -0.0000

Data Index: 1020715 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.2596. Min Act: -0.0000

Data Index: 1152386 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.2364. Min Act: -0.0000

Data Index: 925083 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.2598. Min Act: -0.0000

Data Index: 252417 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 1.5718. Min Range: -1.5718

Max Act: 1.2612. Min Act: -0.0000

Data Index: 491407 (C4 (Web Text))

Max Activating Token Index: 94