Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1494 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.9638. Min Act: -0.0000

Data Index: 388529 (The Pile)

Max Activating Token Index: 477

Text #1

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.9504. Min Act: -0.0000

Data Index: 677228 (The Pile)

Max Activating Token Index: 465

Text #2

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.7523. Min Act: -0.0000

Data Index: 194174 (The Pile)

Max Activating Token Index: 724

Text #3

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.8261. Min Act: -0.0000

Data Index: 480877 (The Pile)

Max Activating Token Index: 677

Text #4

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.7423. Min Act: -0.0000

Data Index: 321697 (The Pile)

Max Activating Token Index: 522

Text #5

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.7141. Min Act: -0.0000

Data Index: 347525 (The Pile)

Max Activating Token Index: 634

Text #6

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.9703. Min Act: -0.0000

Data Index: 1457135 (The Pile)

Max Activating Token Index: 680

Text #7

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.9342. Min Act: -0.0000

Data Index: 1581266 (The Pile)

Max Activating Token Index: 604

Text #8

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.7463. Min Act: -0.0000

Data Index: 1441558 (The Pile)

Max Activating Token Index: 509

Text #9

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.7030. Min Act: -0.0000

Data Index: 277285 (The Pile)

Max Activating Token Index: 541

Text #10

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.6381. Min Act: -0.0000

Data Index: 1959485 (The Pile)

Max Activating Token Index: 639

Text #11

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.6254. Min Act: -0.0000

Data Index: 178604 (The Pile)

Max Activating Token Index: 425

Text #12

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.9008. Min Act: -0.0000

Data Index: 309074 (The Pile)

Max Activating Token Index: 637

Text #13

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.6375. Min Act: -0.0000

Data Index: 711533 (The Pile)

Max Activating Token Index: 780

Text #14

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.5396. Min Act: -0.0000

Data Index: 1746885 (The Pile)

Max Activating Token Index: 629

Text #15

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.7202. Min Act: -0.0000

Data Index: 269333 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.5027. Min Act: -0.0000

Data Index: 167651 (The Pile)

Max Activating Token Index: 917

Text #17

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.6719. Min Act: -0.0000

Data Index: 801444 (The Pile)

Max Activating Token Index: 416

Text #18

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.5408. Min Act: -0.0000

Data Index: 635105 (The Pile)

Max Activating Token Index: 952

Text #19

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.3492. Min Act: -0.0000

Data Index: 1911112 (The Pile)

Max Activating Token Index: 534