Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3039 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.6433. Min Act: -0.0001

Data Index: 202019 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5891. Min Act: -0.0000

Data Index: 858594 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5684. Min Act: -0.0000

Data Index: 148897 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5418. Min Act: -0.0000

Data Index: 882058 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5165. Min Act: -0.0000

Data Index: 835856 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5051. Min Act: -0.0000

Data Index: 586527 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1170923 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1296785 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.5106. Min Act: -0.0000

Data Index: 885716 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.4915. Min Act: -0.0001

Data Index: 476298 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.4767. Min Act: -0.0000

Data Index: 377793 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.4895. Min Act: -0.0000

Data Index: 916992 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.4848. Min Act: -0.0000

Data Index: 337905 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.4838. Min Act: -0.0001

Data Index: 1208599 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.4665. Min Act: -0.0001

Data Index: 262924 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.4688. Min Act: -0.0000

Data Index: 608548 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.4870. Min Act: -0.0001

Data Index: 439637 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.4411. Min Act: -0.0001

Data Index: 793189 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.4963. Min Act: -0.0000

Data Index: 1341090 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.6433. Min Range: -0.6433

Max Act: 0.4691. Min Act: -0.0000

Data Index: 452065 (C4 (Web Text))

Max Activating Token Index: 820