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

Dataset: The Pile

Neuron 3501 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.6211. Min Act: -0.0000

Data Index: 1420764 (The Pile)

Max Activating Token Index: 535

Text #1

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.6374. Min Act: -0.0000

Data Index: 1543550 (The Pile)

Max Activating Token Index: 506

Text #2

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5149. Min Act: -0.0000

Data Index: 925652 (The Pile)

Max Activating Token Index: 382

Text #3

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.5312. Min Act: -0.0000

Data Index: 608044 (The Pile)

Max Activating Token Index: 133

Text #4

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1592716 (The Pile)

Max Activating Token Index: 76

Text #5

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.3648. Min Act: -0.0000

Data Index: 828879 (The Pile)

Max Activating Token Index: 60

Text #6

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1416194 (The Pile)

Max Activating Token Index: 139

Text #7

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.3544. Min Act: -0.0000

Data Index: 813351 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.3004. Min Act: -0.0000

Data Index: 1779799 (The Pile)

Max Activating Token Index: 139

Text #9

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.3244. Min Act: -0.0000

Data Index: 1818407 (The Pile)

Max Activating Token Index: 981

Text #10

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.3089. Min Act: -0.0000

Data Index: 153945 (The Pile)

Max Activating Token Index: 684

Text #11

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.3529. Min Act: -0.0000

Data Index: 913986 (The Pile)

Max Activating Token Index: 204

Text #12

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.2836. Min Act: -0.0000

Data Index: 1188908 (The Pile)

Max Activating Token Index: 64

Text #13

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.2385. Min Act: -0.0000

Data Index: 577292 (The Pile)

Max Activating Token Index: 727

Text #14

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1674680 (The Pile)

Max Activating Token Index: 816

Text #15

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1736350 (The Pile)

Max Activating Token Index: 690

Text #16

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1593556 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.2928. Min Act: -0.0000

Data Index: 1201289 (The Pile)

Max Activating Token Index: 187

Text #18

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.2425. Min Act: -0.0000

Data Index: 201355 (The Pile)

Max Activating Token Index: 220

Text #19

Max Range: 0.6374. Min Range: -0.6374

Max Act: 0.2489. Min Act: -0.0000

Data Index: 77057 (The Pile)

Max Activating Token Index: 531