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

Dataset: The Pile

Neuron 2001 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: 0.4573. Min Range: -0.4573

Max Act: 0.4450. Min Act: -0.0000

Data Index: 831416 (The Pile)

Max Activating Token Index: 384

Text #1

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.4573. Min Act: -0.0000

Data Index: 1592556 (The Pile)

Max Activating Token Index: 767

Text #2

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3786. Min Act: -0.0000

Data Index: 689921 (The Pile)

Max Activating Token Index: 746

Text #3

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1660994 (The Pile)

Max Activating Token Index: 686

Text #4

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3656. Min Act: -0.0000

Data Index: 344313 (The Pile)

Max Activating Token Index: 388

Text #5

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3421. Min Act: -0.0000

Data Index: 1540721 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3514. Min Act: -0.0000

Data Index: 1115974 (The Pile)

Max Activating Token Index: 198

Text #7

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3551. Min Act: -0.0000

Data Index: 1021021 (The Pile)

Max Activating Token Index: 738

Text #8

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3343. Min Act: -0.0000

Data Index: 995295 (The Pile)

Max Activating Token Index: 270

Text #9

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3335. Min Act: -0.0000

Data Index: 994408 (The Pile)

Max Activating Token Index: 347

Text #10

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1194485 (The Pile)

Max Activating Token Index: 812

Text #11

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1009861 (The Pile)

Max Activating Token Index: 777

Text #12

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3494. Min Act: -0.0000

Data Index: 428191 (The Pile)

Max Activating Token Index: 108

Text #13

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3291. Min Act: -0.0000

Data Index: 667758 (The Pile)

Max Activating Token Index: 631

Text #14

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1753677 (The Pile)

Max Activating Token Index: 737

Text #15

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1467198 (The Pile)

Max Activating Token Index: 530

Text #16

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3038. Min Act: -0.0000

Data Index: 179666 (The Pile)

Max Activating Token Index: 771

Text #17

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1147238 (The Pile)

Max Activating Token Index: 510

Text #18

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.2953. Min Act: -0.0000

Data Index: 975584 (The Pile)

Max Activating Token Index: 644

Text #19

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1666860 (The Pile)

Max Activating Token Index: 844