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

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

Neuron 1142 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6755. Min Act: -0.0000

Data Index: 434365 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6073. Min Act: -0.0001

Data Index: 737816 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6408. Min Act: -0.0001

Data Index: 1115234 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6423. Min Act: -0.0000

Data Index: 458021 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6099. Min Act: -0.0001

Data Index: 1275060 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6094. Min Act: -0.0000

Data Index: 15391 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6466. Min Act: -0.0001

Data Index: 241892 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6451. Min Act: -0.0000

Data Index: 958348 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1084996 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6190. Min Act: -0.0000

Data Index: 972558 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6099. Min Act: -0.0001

Data Index: 1040471 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6090. Min Act: -0.0001

Data Index: 160923 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6058. Min Act: -0.0000

Data Index: 308199 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5929. Min Act: -0.0001

Data Index: 227023 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6090. Min Act: -0.0001

Data Index: 581991 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5745. Min Act: -0.0001

Data Index: 640430 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6052. Min Act: -0.0001

Data Index: 1113166 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5986. Min Act: -0.0000

Data Index: 520587 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5829. Min Act: -0.0000

Data Index: 917143 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5754. Min Act: -0.0001

Data Index: 743780 (C4 (Web Text))

Max Activating Token Index: 95