Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3016 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.6973. Min Act: -0.0000

Data Index: 339227 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.5503. Min Act: -0.0000

Data Index: 192873 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.4398. Min Act: -0.0000

Data Index: 600801 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.4870. Min Act: -0.0000

Data Index: 237673 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.4591. Min Act: -0.0000

Data Index: 1290701 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.3353. Min Act: -0.0000

Data Index: 176979 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.3371. Min Act: -0.0000

Data Index: 926280 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.3550. Min Act: -0.0000

Data Index: 422388 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.2877. Min Act: -0.0000

Data Index: 282825 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.2243. Min Act: -0.0000

Data Index: 180098 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.2046. Min Act: -0.0000

Data Index: 1447136 (Python Code)

Max Activating Token Index: 907

Text #11

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.2654. Min Act: -0.0000

Data Index: 1519569 (Python Code)

Max Activating Token Index: 1017

Text #12

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.3064. Min Act: -0.0000

Data Index: 155320 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.2479. Min Act: -0.0000

Data Index: 524210 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.1979. Min Act: -0.0000

Data Index: 652979 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.2990. Min Act: -0.0000

Data Index: 68667 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.1998. Min Act: -0.0000

Data Index: 28133 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.2044. Min Act: -0.0000

Data Index: 1620880 (Python Code)

Max Activating Token Index: 508

Text #18

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.3491. Min Act: -0.0000

Data Index: 708381 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 1.6973. Min Range: -1.6973

Max Act: 1.1305. Min Act: -0.0000

Data Index: 1328924 (C4 (Web Text))

Max Activating Token Index: 393