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

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

Neuron 709 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0791. Min Act: -0.0003

Data Index: 839720 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0730. Min Act: -0.0003

Data Index: 268707 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0693. Min Act: -0.0003

Data Index: 623376 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0653. Min Act: -0.0003

Data Index: 981649 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0660. Min Act: -0.0003

Data Index: 263887 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0649. Min Act: -0.0003

Data Index: 418074 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0641. Min Act: -0.0003

Data Index: 611500 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0637. Min Act: -0.0003

Data Index: 1119716 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0586. Min Act: -0.0003

Data Index: 1088710 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0607. Min Act: -0.0003

Data Index: 527994 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0602. Min Act: -0.0003

Data Index: 914310 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0630. Min Act: -0.0003

Data Index: 268727 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0634. Min Act: -0.0003

Data Index: 540430 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1044456 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0645. Min Act: -0.0003

Data Index: 1091477 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0609. Min Act: -0.0003

Data Index: 506921 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0592. Min Act: -0.0003

Data Index: 676899 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0582. Min Act: -0.0003

Data Index: 1286194 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0597. Min Act: -0.0003

Data Index: 409420 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0583. Min Act: -0.0003

Data Index: 468671 (C4 (Web Text))

Max Activating Token Index: 9