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

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

Neuron 3074 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.5479. Min Act: -0.0001

Data Index: 173643 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.5722. Min Act: -0.0001

Data Index: 1298619 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4553. Min Act: -0.0000

Data Index: 887694 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1305358 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4518. Min Act: -0.0000

Data Index: 15045 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4162. Min Act: -0.0000

Data Index: 931901 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4015. Min Act: -0.0000

Data Index: 142995 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4218. Min Act: -0.0001

Data Index: 855496 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4186. Min Act: -0.0001

Data Index: 203105 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4048. Min Act: -0.0001

Data Index: 1148782 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4129. Min Act: -0.0000

Data Index: 745182 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4110. Min Act: -0.0001

Data Index: 696374 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4045. Min Act: -0.0001

Data Index: 302459 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3912. Min Act: -0.0000

Data Index: 320225 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4015. Min Act: -0.0000

Data Index: 1047207 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3836. Min Act: -0.0001

Data Index: 25154 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3706. Min Act: -0.0000

Data Index: 343513 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4071. Min Act: -0.0000

Data Index: 758766 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4039. Min Act: -0.0000

Data Index: 171306 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3922. Min Act: -0.0000

Data Index: 707828 (C4 (Web Text))

Max Activating Token Index: 760