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

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

Neuron 121 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0519. Min Act: -0.0000

Data Index: 205158 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0517. Min Act: -0.0001

Data Index: 290643 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0518. Min Act: -0.0000

Data Index: 1289802 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0453. Min Act: -0.0000

Data Index: 432296 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0458. Min Act: -0.0000

Data Index: 723731 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0426. Min Act: -0.0000

Data Index: 423867 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0426. Min Act: -0.0000

Data Index: 138354 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0460. Min Act: -0.0001

Data Index: 788678 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0429. Min Act: -0.0001

Data Index: 316803 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0413. Min Act: -0.0001

Data Index: 880124 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0440. Min Act: -0.0000

Data Index: 1047401 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0412. Min Act: -0.0000

Data Index: 210619 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0424. Min Act: -0.0000

Data Index: 1250187 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0424. Min Act: -0.0000

Data Index: 1175689 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0439. Min Act: -0.0001

Data Index: 68922 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0367. Min Act: -0.0000

Data Index: 870768 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0385. Min Act: -0.0000

Data Index: 1463154 (Python Code)

Max Activating Token Index: 613

Text #17

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0385. Min Act: -0.0000

Data Index: 925054 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0389. Min Act: -0.0000

Data Index: 749031 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0386. Min Act: -0.0000

Data Index: 266195 (C4 (Web Text))

Max Activating Token Index: 142