Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5590 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.7184. Min Act: -0.0000

Data Index: 215231 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.6536. Min Act: -0.0000

Data Index: 659898 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.6306. Min Act: -0.0000

Data Index: 567116 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1207971 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5788. Min Act: -0.0000

Data Index: 29878 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1073992 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1068028 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5391. Min Act: -0.0000

Data Index: 930052 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1302085 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5365. Min Act: -0.0000

Data Index: 35539 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5324. Min Act: -0.0000

Data Index: 959257 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5528. Min Act: -0.0000

Data Index: 492279 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5195. Min Act: -0.0000

Data Index: 853684 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4989. Min Act: -0.0000

Data Index: 571914 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5205. Min Act: -0.0000

Data Index: 314914 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1230507 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4939. Min Act: -0.0000

Data Index: 280409 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5060. Min Act: -0.0000

Data Index: 131143 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4841. Min Act: -0.0000

Data Index: 680144 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4632. Min Act: -0.0000

Data Index: 502893 (C4 (Web Text))

Max Activating Token Index: 999