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

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

Neuron 4753 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: 0.3278. Min Range: -0.3278

Max Act: 0.2965. Min Act: -0.0000

Data Index: 21360 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.3278. Min Act: -0.0000

Data Index: 189915 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2886. Min Act: -0.0000

Data Index: 43074 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2510. Min Act: -0.0000

Data Index: 602618 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2903. Min Act: -0.0000

Data Index: 221850 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2803. Min Act: -0.0000

Data Index: 405706 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2681. Min Act: -0.0000

Data Index: 304822 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2636. Min Act: -0.0000

Data Index: 908464 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1025857 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2732. Min Act: -0.0000

Data Index: 921155 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2680. Min Act: -0.0000

Data Index: 12727 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2641. Min Act: -0.0000

Data Index: 335686 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1098776 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2321. Min Act: -0.0000

Data Index: 701771 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2498. Min Act: -0.0000

Data Index: 926607 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2335. Min Act: -0.0000

Data Index: 154527 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2283. Min Act: -0.0000

Data Index: 127180 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2425. Min Act: -0.0000

Data Index: 184919 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2075. Min Act: -0.0000

Data Index: 807817 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.3278. Min Range: -0.3278

Max Act: 0.2363. Min Act: -0.0000

Data Index: 855156 (C4 (Web Text))

Max Activating Token Index: 880