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

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

Neuron 2847 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: 0.7147. Min Range: -0.7147

Max Act: 0.7147. Min Act: -0.0000

Data Index: 861265 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.7147. Min Range: -0.7147

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1487093 (Python Code)

Max Activating Token Index: 881

Text #2

Max Range: 0.7147. Min Range: -0.7147

Max Act: 0.5552. Min Act: -0.0000

Data Index: 1223801 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.7147. Min Range: -0.7147

Max Act: 0.5030. Min Act: -0.0000

Data Index: 867419 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.7147. Min Range: -0.7147

Max Act: 0.4872. Min Act: -0.0000

Data Index: 567406 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.7147. Min Range: -0.7147

Max Act: 0.4595. Min Act: -0.0000

Data Index: 938592 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.7147. Min Range: -0.7147

Max Act: 0.4711. Min Act: -0.0000

Data Index: 842866 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.7147. Min Range: -0.7147

Max Act: 0.4376. Min Act: -0.0000

Data Index: 1434131 (Python Code)

Max Activating Token Index: 331

Text #8

Max Range: 0.7147. Min Range: -0.7147

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1600932 (Python Code)

Max Activating Token Index: 579

Text #9

Max Range: 0.7147. Min Range: -0.7147

Max Act: 0.4415. Min Act: -0.0000

Data Index: 358931 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.7147. Min Range: -0.7147

Max Act: 0.4303. Min Act: -0.0000

Data Index: 221438 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 0.7147. Min Range: -0.7147

Max Act: 0.4162. Min Act: -0.0000

Data Index: 875348 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.7147. Min Range: -0.7147

Max Act: 0.4454. Min Act: -0.0000

Data Index: 196905 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.7147. Min Range: -0.7147

Max Act: 0.4545. Min Act: -0.0000

Data Index: 210651 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.7147. Min Range: -0.7147

Max Act: 0.4190. Min Act: -0.0000

Data Index: 1355735 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.7147. Min Range: -0.7147

Max Act: 0.4035. Min Act: -0.0000

Data Index: 438838 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.7147. Min Range: -0.7147

Max Act: 0.4261. Min Act: -0.0000

Data Index: 850350 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 0.7147. Min Range: -0.7147

Max Act: 0.4124. Min Act: -0.0000

Data Index: 7283 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 0.7147. Min Range: -0.7147

Max Act: 0.3697. Min Act: -0.0000

Data Index: 660834 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.7147. Min Range: -0.7147

Max Act: 0.3985. Min Act: -0.0000

Data Index: 1510734 (Python Code)

Max Activating Token Index: 358