Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3049 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.5285. Min Act: -0.0001

Data Index: 625089 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.5279. Min Act: -0.0001

Data Index: 263733 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4886. Min Act: -0.0001

Data Index: 1087294 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4905. Min Act: -0.0001

Data Index: 655005 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.5135. Min Act: -0.0001

Data Index: 373618 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.5439. Min Act: -0.0001

Data Index: 861269 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4863. Min Act: -0.0001

Data Index: 808446 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4923. Min Act: -0.0001

Data Index: 67373 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4920. Min Act: -0.0001

Data Index: 350382 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.5451. Min Act: -0.0001

Data Index: 1250867 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4858. Min Act: -0.0001

Data Index: 895997 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4464. Min Act: -0.0001

Data Index: 387389 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4872. Min Act: -0.0001

Data Index: 63637 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4721. Min Act: -0.0001

Data Index: 261522 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4776. Min Act: -0.0001

Data Index: 814800 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4686. Min Act: -0.0001

Data Index: 96534 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.5216. Min Act: -0.0001

Data Index: 45557 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4634. Min Act: -0.0001

Data Index: 946819 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.5003. Min Act: -0.0001

Data Index: 295566 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4493. Min Act: -0.0001

Data Index: 523045 (C4 (Web Text))

Max Activating Token Index: 409