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

Dataset: The Pile

Neuron 1704 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7818. Min Act: -0.0000

Data Index: 390174 (The Pile)

Max Activating Token Index: 151

Text #1

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1340485 (The Pile)

Max Activating Token Index: 354

Text #2

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1863382 (The Pile)

Max Activating Token Index: 640

Text #3

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7456. Min Act: -0.0000

Data Index: 540199 (The Pile)

Max Activating Token Index: 522

Text #4

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7470. Min Act: -0.0000

Data Index: 5493 (The Pile)

Max Activating Token Index: 654

Text #5

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7239. Min Act: -0.0000

Data Index: 5360 (The Pile)

Max Activating Token Index: 865

Text #6

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7491. Min Act: -0.0000

Data Index: 305342 (The Pile)

Max Activating Token Index: 128

Text #7

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1528887 (The Pile)

Max Activating Token Index: 1006

Text #8

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7486. Min Act: -0.0000

Data Index: 1844361 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7314. Min Act: -0.0000

Data Index: 886144 (The Pile)

Max Activating Token Index: 743

Text #10

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7266. Min Act: -0.0000

Data Index: 412151 (The Pile)

Max Activating Token Index: 480

Text #11

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1021385 (The Pile)

Max Activating Token Index: 677

Text #12

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7053. Min Act: -0.0000

Data Index: 293775 (The Pile)

Max Activating Token Index: 169

Text #13

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1123972 (The Pile)

Max Activating Token Index: 604

Text #14

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1126315 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1803549 (The Pile)

Max Activating Token Index: 455

Text #16

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1381629 (The Pile)

Max Activating Token Index: 954

Text #17

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6789. Min Act: -0.0000

Data Index: 218243 (The Pile)

Max Activating Token Index: 766

Text #18

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6721. Min Act: -0.0000

Data Index: 845734 (The Pile)

Max Activating Token Index: 983

Text #19

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1366737 (The Pile)

Max Activating Token Index: 993