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

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

Neuron 2014 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.5031. Min Act: -0.0002

Data Index: 1006116 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4879. Min Act: -0.0002

Data Index: 55329 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4952. Min Act: -0.0002

Data Index: 728886 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3840. Min Act: -0.0002

Data Index: 698138 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4674. Min Act: -0.0002

Data Index: 110025 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4924. Min Act: -0.0001

Data Index: 737128 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4326. Min Act: -0.0002

Data Index: 739462 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4687. Min Act: -0.0002

Data Index: 39127 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4406. Min Act: -0.0001

Data Index: 814920 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4507. Min Act: -0.0002

Data Index: 1168378 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3847. Min Act: -0.0002

Data Index: 636355 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4076. Min Act: -0.0002

Data Index: 1193981 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4134. Min Act: -0.0001

Data Index: 647197 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.3909. Min Act: -0.0002

Data Index: 828066 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4227. Min Act: -0.0002

Data Index: 336001 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4547. Min Act: -0.0001

Data Index: 434349 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4350. Min Act: -0.0002

Data Index: 530670 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4085. Min Act: -0.0001

Data Index: 1514117 (Python Code)

Max Activating Token Index: 634

Text #18

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4030. Min Act: -0.0002

Data Index: 259069 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.5031. Min Range: -0.5031

Max Act: 0.4336. Min Act: -0.0001

Data Index: 114544 (C4 (Web Text))

Max Activating Token Index: 287