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

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

Neuron 2007 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3553. Min Range: -1.3553

Max Act: 1.3553. Min Act: -0.0001

Data Index: 764212 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 1.3553. Min Range: -1.3553

Max Act: 0.9927. Min Act: -0.0001

Data Index: 61048 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 1.3553. Min Range: -1.3553

Max Act: 0.9638. Min Act: -0.0001

Data Index: 231077 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 1.3553. Min Range: -1.3553

Max Act: 0.8528. Min Act: -0.0001

Data Index: 1155812 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 1.3553. Min Range: -1.3553

Max Act: 0.8436. Min Act: -0.0001

Data Index: 1132476 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.3553. Min Range: -1.3553

Max Act: 0.8412. Min Act: -0.0001

Data Index: 856094 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 1.3553. Min Range: -1.3553

Max Act: 0.7781. Min Act: -0.0000

Data Index: 656580 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 1.3553. Min Range: -1.3553

Max Act: 0.7878. Min Act: -0.0001

Data Index: 605012 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 1.3553. Min Range: -1.3553

Max Act: 0.7054. Min Act: -0.0001

Data Index: 363028 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 1.3553. Min Range: -1.3553

Max Act: 0.7694. Min Act: -0.0001

Data Index: 100341 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 1.3553. Min Range: -1.3553

Max Act: 0.7153. Min Act: -0.0001

Data Index: 1185888 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 1.3553. Min Range: -1.3553

Max Act: 0.6835. Min Act: -0.0001

Data Index: 456872 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 1.3553. Min Range: -1.3553

Max Act: 0.6671. Min Act: -0.0001

Data Index: 350111 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 1.3553. Min Range: -1.3553

Max Act: 0.6921. Min Act: -0.0000

Data Index: 884684 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 1.3553. Min Range: -1.3553

Max Act: 0.6046. Min Act: -0.0001

Data Index: 1138986 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 1.3553. Min Range: -1.3553

Max Act: 0.6654. Min Act: -0.0001

Data Index: 1316630 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 1.3553. Min Range: -1.3553

Max Act: 0.5994. Min Act: -0.0001

Data Index: 749805 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 1.3553. Min Range: -1.3553

Max Act: 0.6598. Min Act: -0.0001

Data Index: 796606 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 1.3553. Min Range: -1.3553

Max Act: 0.6197. Min Act: -0.0001

Data Index: 1189672 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 1.3553. Min Range: -1.3553

Max Act: 0.6874. Min Act: -0.0000

Data Index: 525109 (C4 (Web Text))

Max Activating Token Index: 323