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

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

Neuron 1414 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0635. Min Act: -0.0001

Data Index: 983146 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0672. Min Act: -0.0001

Data Index: 301276 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0576. Min Act: -0.0001

Data Index: 401134 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1160362 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0557. Min Act: -0.0001

Data Index: 259618 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1403178 (Python Code)

Max Activating Token Index: 864

Text #6

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0537. Min Act: -0.0001

Data Index: 107663 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0572. Min Act: -0.0001

Data Index: 133917 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0531. Min Act: -0.0001

Data Index: 983940 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0574. Min Act: -0.0001

Data Index: 1287233 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0576. Min Act: -0.0001

Data Index: 908427 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0536. Min Act: -0.0001

Data Index: 71532 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0520. Min Act: -0.0001

Data Index: 324466 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0522. Min Act: -0.0001

Data Index: 1077972 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0499. Min Act: -0.0001

Data Index: 1137382 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0524. Min Act: -0.0001

Data Index: 927971 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0540. Min Act: -0.0001

Data Index: 173941 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0499. Min Act: -0.0001

Data Index: 1380834 (Python Code)

Max Activating Token Index: 523

Text #18

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0512. Min Act: -0.0001

Data Index: 1202214 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0470. Min Act: -0.0001

Data Index: 1551644 (Python Code)

Max Activating Token Index: 800