Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4124 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1669. Min Range: -1.1669

Max Act: 1.1492. Min Act: -0.0000

Data Index: 1368781 (The Pile)

Max Activating Token Index: 888

Text #1

Max Range: 1.1669. Min Range: -1.1669

Max Act: 1.1388. Min Act: -0.0000

Data Index: 438424 (The Pile)

Max Activating Token Index: 358

Text #2

Max Range: 1.1669. Min Range: -1.1669

Max Act: 1.0660. Min Act: -0.0000

Data Index: 1966799 (The Pile)

Max Activating Token Index: 581

Text #3

Max Range: 1.1669. Min Range: -1.1669

Max Act: 1.1669. Min Act: -0.0000

Data Index: 1662743 (The Pile)

Max Activating Token Index: 758

Text #4

Max Range: 1.1669. Min Range: -1.1669

Max Act: 1.0762. Min Act: -0.0000

Data Index: 1385168 (The Pile)

Max Activating Token Index: 515

Text #5

Max Range: 1.1669. Min Range: -1.1669

Max Act: 1.0096. Min Act: -0.0000

Data Index: 864684 (The Pile)

Max Activating Token Index: 416

Text #6

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9987. Min Act: -0.0000

Data Index: 723038 (The Pile)

Max Activating Token Index: 406

Text #7

Max Range: 1.1669. Min Range: -1.1669

Max Act: 1.0036. Min Act: -0.0000

Data Index: 1717326 (The Pile)

Max Activating Token Index: 705

Text #8

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1618835 (The Pile)

Max Activating Token Index: 686

Text #9

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9287. Min Act: -0.0000

Data Index: 332200 (The Pile)

Max Activating Token Index: 460

Text #10

Max Range: 1.1669. Min Range: -1.1669

Max Act: 1.0318. Min Act: -0.0000

Data Index: 734479 (The Pile)

Max Activating Token Index: 194

Text #11

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9350. Min Act: -0.0000

Data Index: 437154 (The Pile)

Max Activating Token Index: 381

Text #12

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.8791. Min Act: -0.0000

Data Index: 1989671 (The Pile)

Max Activating Token Index: 107

Text #13

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9223. Min Act: -0.0000

Data Index: 652248 (The Pile)

Max Activating Token Index: 302

Text #14

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.7813. Min Act: -0.0000

Data Index: 723708 (The Pile)

Max Activating Token Index: 978

Text #15

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9377. Min Act: -0.0000

Data Index: 432815 (The Pile)

Max Activating Token Index: 8

Text #16

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.9078. Min Act: -0.0000

Data Index: 1681497 (The Pile)

Max Activating Token Index: 400

Text #17

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.8634. Min Act: -0.0000

Data Index: 1278830 (The Pile)

Max Activating Token Index: 465

Text #18

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.8585. Min Act: -0.0000

Data Index: 593911 (The Pile)

Max Activating Token Index: 457

Text #19

Max Range: 1.1669. Min Range: -1.1669

Max Act: 0.7785. Min Act: -0.0000

Data Index: 224264 (The Pile)

Max Activating Token Index: 772