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

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

Neuron 3424 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0969. Min Range: -2.0969

Max Act: 2.0969. Min Act: -0.0001

Data Index: 283096 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 2.0969. Min Range: -2.0969

Max Act: 2.0252. Min Act: -0.0001

Data Index: 52016 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 2.0969. Min Range: -2.0969

Max Act: 1.6550. Min Act: -0.0001

Data Index: 505477 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 2.0969. Min Range: -2.0969

Max Act: 1.6940. Min Act: -0.0000

Data Index: 1192109 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 2.0969. Min Range: -2.0969

Max Act: 1.7535. Min Act: -0.0000

Data Index: 324466 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 2.0969. Min Range: -2.0969

Max Act: 1.6070. Min Act: -0.0000

Data Index: 1233994 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 2.0969. Min Range: -2.0969

Max Act: 1.6839. Min Act: -0.0000

Data Index: 775883 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 2.0969. Min Range: -2.0969

Max Act: 1.8377. Min Act: -0.0000

Data Index: 132154 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 2.0969. Min Range: -2.0969

Max Act: 1.6770. Min Act: -0.0001

Data Index: 508454 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 2.0969. Min Range: -2.0969

Max Act: 1.6787. Min Act: -0.0001

Data Index: 340964 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 2.0969. Min Range: -2.0969

Max Act: 1.8054. Min Act: -0.0000

Data Index: 1095506 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 2.0969. Min Range: -2.0969

Max Act: 1.6339. Min Act: -0.0000

Data Index: 680350 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 2.0969. Min Range: -2.0969

Max Act: 1.6521. Min Act: -0.0001

Data Index: 1081573 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 2.0969. Min Range: -2.0969

Max Act: 1.5921. Min Act: -0.0001

Data Index: 545432 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 2.0969. Min Range: -2.0969

Max Act: 1.4871. Min Act: -0.0000

Data Index: 746389 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 2.0969. Min Range: -2.0969

Max Act: 1.5865. Min Act: -0.0001

Data Index: 258888 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 2.0969. Min Range: -2.0969

Max Act: 1.6647. Min Act: -0.0001

Data Index: 455759 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 2.0969. Min Range: -2.0969

Max Act: 1.4694. Min Act: -0.0000

Data Index: 79005 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 2.0969. Min Range: -2.0969

Max Act: 1.5290. Min Act: -0.0001

Data Index: 69319 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 2.0969. Min Range: -2.0969

Max Act: 1.4889. Min Act: -0.0000

Data Index: 711010 (C4 (Web Text))

Max Activating Token Index: 114