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

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

Neuron 4158 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.6092. Min Act: -0.0000

Data Index: 762246 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1339365 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1067698 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3875. Min Act: -0.0000

Data Index: 306274 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4002. Min Act: -0.0000

Data Index: 1332211 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1483152 (Python Code)

Max Activating Token Index: 873

Text #6

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3814. Min Act: -0.0000

Data Index: 466053 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3909. Min Act: -0.0000

Data Index: 991339 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3869. Min Act: -0.0000

Data Index: 635074 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3858. Min Act: -0.0000

Data Index: 234024 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3682. Min Act: -0.0000

Data Index: 1408793 (Python Code)

Max Activating Token Index: 474

Text #11

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3422. Min Act: -0.0000

Data Index: 607034 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1472862 (Python Code)

Max Activating Token Index: 209

Text #13

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3337. Min Act: -0.0000

Data Index: 688267 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1256371 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1159385 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3589. Min Act: -0.0000

Data Index: 349476 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3155. Min Act: -0.0000

Data Index: 825051 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1234540 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.3199. Min Act: -0.0000

Data Index: 189074 (C4 (Web Text))

Max Activating Token Index: 734