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

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

Neuron 254 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.9882. Min Act: 0.0000

Data Index: 593672 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8799. Min Act: -0.0000

Data Index: 321490 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.6681. Min Act: -0.0000

Data Index: 1157654 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.6161. Min Act: -0.0000

Data Index: 608395 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.5471. Min Act: -0.0000

Data Index: 526100 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.6157. Min Act: -0.0000

Data Index: 673815 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.5976. Min Act: -0.0000

Data Index: 571168 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.5859. Min Act: 0.0000

Data Index: 1200469 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1213504 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.5329. Min Act: -0.0000

Data Index: 412106 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.5266. Min Act: -0.0000

Data Index: 956840 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.5050. Min Act: 0.0000

Data Index: 959428 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.4904. Min Act: -0.0000

Data Index: 69029 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.4917. Min Act: 0.0000

Data Index: 1139533 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.4922. Min Act: 0.0000

Data Index: 1330063 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.4600. Min Act: -0.0000

Data Index: 647413 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.4856. Min Act: -0.0000

Data Index: 639135 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.4644. Min Act: -0.0000

Data Index: 813041 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1002673 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.4625. Min Act: 0.0000

Data Index: 886471 (C4 (Web Text))

Max Activating Token Index: 532