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

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

Neuron 5725 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.6747. Min Act: -0.0000

Data Index: 235727 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.8437. Min Act: -0.0000

Data Index: 925974 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.7922. Min Act: -0.0000

Data Index: 1348266 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.5369. Min Act: -0.0000

Data Index: 1326770 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.6021. Min Act: -0.0000

Data Index: 978887 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.4980. Min Act: -0.0000

Data Index: 1097857 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.5026. Min Act: -0.0000

Data Index: 847772 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.4854. Min Act: -0.0000

Data Index: 157250 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.4591. Min Act: -0.0000

Data Index: 860526 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.3592. Min Act: -0.0000

Data Index: 664501 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.4436. Min Act: -0.0000

Data Index: 590877 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.5189. Min Act: -0.0000

Data Index: 1030384 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.2855. Min Act: -0.0000

Data Index: 1295863 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.3524. Min Act: -0.0000

Data Index: 927867 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.2790. Min Act: -0.0000

Data Index: 848468 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.4154. Min Act: -0.0000

Data Index: 1094188 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.3425. Min Act: -0.0000

Data Index: 698818 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.2448. Min Act: -0.0000

Data Index: 814608 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.3924. Min Act: -0.0000

Data Index: 524 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 1.8437. Min Range: -1.8437

Max Act: 1.3164. Min Act: -0.0000

Data Index: 457143 (C4 (Web Text))

Max Activating Token Index: 785