Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1237 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.3162. Min Act: -0.0000

Data Index: 337990 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2991. Min Act: 0.0000

Data Index: 1122746 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2889. Min Act: -0.0001

Data Index: 248454 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2633. Min Act: -0.0001

Data Index: 81267 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2474. Min Act: -0.0000

Data Index: 210084 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1007514 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2433. Min Act: -0.0000

Data Index: 224451 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2417. Min Act: -0.0000

Data Index: 764993 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2208. Min Act: -0.0001

Data Index: 58902 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2120. Min Act: -0.0000

Data Index: 311221 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2245. Min Act: -0.0000

Data Index: 684352 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2146. Min Act: 0.0001

Data Index: 709891 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2050. Min Act: -0.0000

Data Index: 523757 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2387. Min Act: -0.0000

Data Index: 362155 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2379. Min Act: -0.0001

Data Index: 739457 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2331. Min Act: -0.0001

Data Index: 797734 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2142. Min Act: -0.0001

Data Index: 956788 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1331356 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2213. Min Act: -0.0000

Data Index: 179650 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2057. Min Act: -0.0000

Data Index: 457412 (C4 (Web Text))

Max Activating Token Index: 584