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

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

Neuron 4374 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3426. Min Act: -0.0000

Data Index: 1036274 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3636. Min Act: -0.0000

Data Index: 1106360 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3382. Min Act: -0.0000

Data Index: 721494 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3284. Min Act: -0.0000

Data Index: 709493 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3362. Min Act: -0.0000

Data Index: 37378 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2855. Min Act: -0.0000

Data Index: 356324 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3025. Min Act: -0.0000

Data Index: 72945 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1602192 (Python Code)

Max Activating Token Index: 19

Text #8

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1334658 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2812. Min Act: -0.0000

Data Index: 427892 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2907. Min Act: -0.0000

Data Index: 128629 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2915. Min Act: -0.0000

Data Index: 1014694 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2964. Min Act: -0.0000

Data Index: 545319 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2884. Min Act: -0.0000

Data Index: 445863 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2793. Min Act: -0.0000

Data Index: 795197 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2856. Min Act: -0.0000

Data Index: 408690 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1559451 (Python Code)

Max Activating Token Index: 382

Text #17

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2844. Min Act: -0.0000

Data Index: 1129188 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2829. Min Act: -0.0000

Data Index: 727879 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.3636. Min Range: -0.3636

Max Act: 0.2745. Min Act: -0.0000

Data Index: 50624 (C4 (Web Text))

Max Activating Token Index: 285