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

Dataset: The Pile

Neuron 3330 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.1596. Min Act: -0.0000

Data Index: 1187156 (The Pile)

Max Activating Token Index: 203

Text #1

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9661. Min Act: -0.0000

Data Index: 150336 (The Pile)

Max Activating Token Index: 780

Text #2

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8141. Min Act: -0.0000

Data Index: 293391 (The Pile)

Max Activating Token Index: 865

Text #3

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8074. Min Act: -0.0000

Data Index: 33212 (The Pile)

Max Activating Token Index: 453

Text #4

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1963809 (The Pile)

Max Activating Token Index: 935

Text #5

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7663. Min Act: -0.0000

Data Index: 1817454 (The Pile)

Max Activating Token Index: 625

Text #6

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7579. Min Act: -0.0000

Data Index: 912773 (The Pile)

Max Activating Token Index: 646

Text #7

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8142. Min Act: -0.0000

Data Index: 190805 (The Pile)

Max Activating Token Index: 213

Text #8

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7224. Min Act: -0.0000

Data Index: 919556 (The Pile)

Max Activating Token Index: 540

Text #9

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1593378 (The Pile)

Max Activating Token Index: 988

Text #10

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.6655. Min Act: -0.0000

Data Index: 1002502 (The Pile)

Max Activating Token Index: 790

Text #11

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7337. Min Act: -0.0000

Data Index: 557084 (The Pile)

Max Activating Token Index: 538

Text #12

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.6535. Min Act: -0.0000

Data Index: 986731 (The Pile)

Max Activating Token Index: 715

Text #13

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.6894. Min Act: -0.0000

Data Index: 353192 (The Pile)

Max Activating Token Index: 299

Text #14

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.6221. Min Act: -0.0000

Data Index: 62986 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.6587. Min Act: -0.0000

Data Index: 1079381 (The Pile)

Max Activating Token Index: 143

Text #16

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.6821. Min Act: -0.0000

Data Index: 575777 (The Pile)

Max Activating Token Index: 751

Text #17

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.6761. Min Act: -0.0000

Data Index: 952444 (The Pile)

Max Activating Token Index: 771

Text #18

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.6034. Min Act: -0.0000

Data Index: 437597 (The Pile)

Max Activating Token Index: 915

Text #19

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.6264. Min Act: -0.0000

Data Index: 962171 (The Pile)

Max Activating Token Index: 552