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

Dataset: The Pile

Neuron 26 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6794. Min Act: -0.0000

Data Index: 1386618 (The Pile)

Max Activating Token Index: 501

Text #1

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6378. Min Act: -0.0000

Data Index: 1310474 (The Pile)

Max Activating Token Index: 887

Text #2

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.5100. Min Act: -0.0001

Data Index: 1139755 (The Pile)

Max Activating Token Index: 742

Text #3

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.5120. Min Act: -0.0000

Data Index: 1026544 (The Pile)

Max Activating Token Index: 202

Text #4

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.5030. Min Act: -0.0000

Data Index: 1010967 (The Pile)

Max Activating Token Index: 626

Text #5

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.4458. Min Act: -0.0000

Data Index: 1508353 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.4145. Min Act: -0.0000

Data Index: 559305 (The Pile)

Max Activating Token Index: 402

Text #7

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.3502. Min Act: -0.0000

Data Index: 726591 (The Pile)

Max Activating Token Index: 986

Text #8

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.3450. Min Act: -0.0000

Data Index: 1866222 (The Pile)

Max Activating Token Index: 526

Text #9

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.3015. Min Act: -0.0000

Data Index: 668976 (The Pile)

Max Activating Token Index: 437

Text #10

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.2634. Min Act: -0.0000

Data Index: 653138 (The Pile)

Max Activating Token Index: 260

Text #11

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.2974. Min Act: -0.0000

Data Index: 872825 (The Pile)

Max Activating Token Index: 232

Text #12

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.2463. Min Act: -0.0000

Data Index: 1448098 (The Pile)

Max Activating Token Index: 512

Text #13

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.2164. Min Act: -0.0001

Data Index: 1209459 (The Pile)

Max Activating Token Index: 518

Text #14

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.2338. Min Act: -0.0000

Data Index: 793144 (The Pile)

Max Activating Token Index: 810

Text #15

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.2533. Min Act: -0.0000

Data Index: 1825955 (The Pile)

Max Activating Token Index: 574

Text #16

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.1807. Min Act: -0.0000

Data Index: 1128935 (The Pile)

Max Activating Token Index: 909

Text #17

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.2504. Min Act: -0.0000

Data Index: 123852 (The Pile)

Max Activating Token Index: 171

Text #18

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.2894. Min Act: -0.0000

Data Index: 1743441 (The Pile)

Max Activating Token Index: 637

Text #19

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.1771. Min Act: -0.0001

Data Index: 1505237 (The Pile)

Max Activating Token Index: 107