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

Dataset: The Pile

Neuron 1418 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.7138. Min Act: -0.0000

Data Index: 568402 (The Pile)

Max Activating Token Index: 319

Text #1

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.7643. Min Act: -0.0000

Data Index: 1112893 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.6476. Min Act: -0.0000

Data Index: 1637615 (The Pile)

Max Activating Token Index: 225

Text #3

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.6445. Min Act: -0.0000

Data Index: 960640 (The Pile)

Max Activating Token Index: 997

Text #4

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.4997. Min Act: -0.0000

Data Index: 1822179 (The Pile)

Max Activating Token Index: 852

Text #5

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.4937. Min Act: -0.0000

Data Index: 940077 (The Pile)

Max Activating Token Index: 271

Text #6

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.3293. Min Act: -0.0000

Data Index: 1682544 (The Pile)

Max Activating Token Index: 328

Text #7

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.3375. Min Act: -0.0000

Data Index: 364950 (The Pile)

Max Activating Token Index: 62

Text #8

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.2442. Min Act: -0.0000

Data Index: 608409 (The Pile)

Max Activating Token Index: 524

Text #9

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.2621. Min Act: -0.0000

Data Index: 1341849 (The Pile)

Max Activating Token Index: 624

Text #10

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.2499. Min Act: -0.0000

Data Index: 786335 (The Pile)

Max Activating Token Index: 43

Text #11

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.1332. Min Act: -0.0000

Data Index: 522497 (The Pile)

Max Activating Token Index: 329

Text #12

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.3455. Min Act: -0.0000

Data Index: 389686 (The Pile)

Max Activating Token Index: 337

Text #13

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.1795. Min Act: -0.0000

Data Index: 1056720 (The Pile)

Max Activating Token Index: 895

Text #14

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.2404. Min Act: -0.0000

Data Index: 581664 (The Pile)

Max Activating Token Index: 784

Text #15

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.2812. Min Act: -0.0000

Data Index: 953271 (The Pile)

Max Activating Token Index: 56

Text #16

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.2136. Min Act: -0.0000

Data Index: 950955 (The Pile)

Max Activating Token Index: 456

Text #17

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.2638. Min Act: -0.0000

Data Index: 1897930 (The Pile)

Max Activating Token Index: 483

Text #18

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.1500. Min Act: -0.0000

Data Index: 379313 (The Pile)

Max Activating Token Index: 616

Text #19

Max Range: 1.7643. Min Range: -1.7643

Max Act: 1.0964. Min Act: -0.0000

Data Index: 408880 (The Pile)

Max Activating Token Index: 219