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

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

Neuron 5106 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: 0.7178. Min Range: -0.7178

Max Act: 0.7178. Min Act: -0.0000

Data Index: 927550 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.5902. Min Act: -0.0000

Data Index: 696801 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.5505. Min Act: 0.0000

Data Index: 1344394 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.5518. Min Act: 0.0000

Data Index: 134916 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1451382 (Python Code)

Max Activating Token Index: 763

Text #5

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.5027. Min Act: 0.0002

Data Index: 654400 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.5086. Min Act: -0.0000

Data Index: 885743 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4685. Min Act: 0.0000

Data Index: 238251 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4664. Min Act: -0.0000

Data Index: 485146 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4431. Min Act: -0.0000

Data Index: 571327 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4276. Min Act: -0.0000

Data Index: 72523 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4403. Min Act: -0.0000

Data Index: 647049 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4410. Min Act: -0.0000

Data Index: 224218 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4387. Min Act: -0.0000

Data Index: 40662 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4378. Min Act: 0.0000

Data Index: 1232069 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4324. Min Act: 0.0000

Data Index: 533646 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4298. Min Act: -0.0000

Data Index: 676300 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4302. Min Act: -0.0000

Data Index: 595014 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4186. Min Act: 0.0000

Data Index: 579233 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4249. Min Act: 0.0003

Data Index: 1256097 (C4 (Web Text))

Max Activating Token Index: 651