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

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

Neuron 1644 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: 0.0964. Min Range: -0.0964

Max Act: 0.0964. Min Act: -0.0003

Data Index: 479723 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0728. Min Act: -0.0003

Data Index: 934510 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0719. Min Act: -0.0003

Data Index: 1322705 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0704. Min Act: -0.0003

Data Index: 233342 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0695. Min Act: -0.0003

Data Index: 224223 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0697. Min Act: -0.0003

Data Index: 448073 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0674. Min Act: -0.0003

Data Index: 881741 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0681. Min Act: -0.0003

Data Index: 82029 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0670. Min Act: -0.0003

Data Index: 372643 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0613. Min Act: -0.0003

Data Index: 745051 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0637. Min Act: -0.0003

Data Index: 106173 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0645. Min Act: -0.0003

Data Index: 820334 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0647. Min Act: -0.0003

Data Index: 1126160 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0661. Min Act: -0.0003

Data Index: 668851 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0669. Min Act: -0.0003

Data Index: 4342 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0643. Min Act: -0.0003

Data Index: 592711 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0665. Min Act: -0.0003

Data Index: 610230 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0659. Min Act: -0.0003

Data Index: 872109 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0639. Min Act: -0.0003

Data Index: 488710 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0640. Min Act: -0.0003

Data Index: 237502 (C4 (Web Text))

Max Activating Token Index: 429