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

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

Neuron 1192 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: 0.4701. Min Range: -0.4701

Max Act: 0.4701. Min Act: -0.0001

Data Index: 1447080 (Python Code)

Max Activating Token Index: 739

Text #1

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3934. Min Act: -0.0001

Data Index: 1469426 (Python Code)

Max Activating Token Index: 1015

Text #2

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3625. Min Act: -0.0000

Data Index: 720371 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3608. Min Act: -0.0001

Data Index: 1546551 (Python Code)

Max Activating Token Index: 456

Text #4

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3415. Min Act: -0.0001

Data Index: 777512 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3139. Min Act: -0.0000

Data Index: 601495 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3098. Min Act: -0.0000

Data Index: 17000 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3067. Min Act: -0.0000

Data Index: 495492 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3176. Min Act: -0.0000

Data Index: 1064492 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3046. Min Act: -0.0000

Data Index: 933982 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3104. Min Act: -0.0000

Data Index: 637695 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2845. Min Act: -0.0000

Data Index: 259330 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3030. Min Act: -0.0001

Data Index: 194954 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2997. Min Act: -0.0001

Data Index: 1549069 (Python Code)

Max Activating Token Index: 553

Text #14

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3080. Min Act: -0.0000

Data Index: 788234 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2958. Min Act: -0.0000

Data Index: 394070 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2957. Min Act: -0.0001

Data Index: 1592646 (Python Code)

Max Activating Token Index: 78

Text #17

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2944. Min Act: -0.0000

Data Index: 761428 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2935. Min Act: -0.0000

Data Index: 175466 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2957. Min Act: -0.0000

Data Index: 538342 (C4 (Web Text))

Max Activating Token Index: 900