Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1426 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1061736 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0640. Min Act: -0.0002

Data Index: 731054 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0575. Min Act: -0.0002

Data Index: 417702 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1062943 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0647. Min Act: -0.0002

Data Index: 545429 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0662. Min Act: -0.0002

Data Index: 1183948 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0630. Min Act: -0.0002

Data Index: 630065 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1155593 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0639. Min Act: -0.0002

Data Index: 1119720 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0643. Min Act: -0.0002

Data Index: 2568 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1287694 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0606. Min Act: -0.0002

Data Index: 788972 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0609. Min Act: -0.0001

Data Index: 32323 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0595. Min Act: -0.0002

Data Index: 403714 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0609. Min Act: -0.0002

Data Index: 796331 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0554. Min Act: -0.0002

Data Index: 529648 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0571. Min Act: -0.0002

Data Index: 998044 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1341300 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0534. Min Act: -0.0002

Data Index: 772281 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0569. Min Act: -0.0002

Data Index: 861232 (C4 (Web Text))

Max Activating Token Index: 36