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

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

Neuron 4863 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.5004. Min Act: -0.0000

Data Index: 364172 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1087778 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.5006. Min Act: -0.0000

Data Index: 741912 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.4606. Min Act: -0.0000

Data Index: 530238 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.4585. Min Act: -0.0000

Data Index: 1009496 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.4980. Min Act: -0.0000

Data Index: 538379 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1261412 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.4254. Min Act: -0.0000

Data Index: 899588 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.4015. Min Act: -0.0000

Data Index: 483403 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.4330. Min Act: -0.0000

Data Index: 148562 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.4112. Min Act: -0.0000

Data Index: 981148 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.4094. Min Act: -0.0000

Data Index: 98063 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.4048. Min Act: -0.0000

Data Index: 180033 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.4222. Min Act: -0.0000

Data Index: 750714 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.3918. Min Act: -0.0000

Data Index: 131793 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.4033. Min Act: -0.0000

Data Index: 1011396 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.4463. Min Act: -0.0000

Data Index: 1274689 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.4169. Min Act: -0.0000

Data Index: 1016048 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.4094. Min Act: -0.0000

Data Index: 1217483 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.5024. Min Range: -0.5024

Max Act: 0.4181. Min Act: -0.0000

Data Index: 860466 (C4 (Web Text))

Max Activating Token Index: 875