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

Dataset: The Pile

Neuron 3173 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: 1.0480. Min Range: -1.0480

Max Act: 1.0480. Min Act: -0.0000

Data Index: 935934 (The Pile)

Max Activating Token Index: 495

Text #1

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8512. Min Act: -0.0000

Data Index: 1307939 (The Pile)

Max Activating Token Index: 192

Text #2

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8879. Min Act: -0.0000

Data Index: 997668 (The Pile)

Max Activating Token Index: 392

Text #3

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8505. Min Act: -0.0000

Data Index: 1351695 (The Pile)

Max Activating Token Index: 923

Text #4

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1905701 (The Pile)

Max Activating Token Index: 505

Text #5

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7906. Min Act: -0.0000

Data Index: 1609225 (The Pile)

Max Activating Token Index: 824

Text #6

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1791035 (The Pile)

Max Activating Token Index: 779

Text #7

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1470492 (The Pile)

Max Activating Token Index: 694

Text #8

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8079. Min Act: -0.0000

Data Index: 1660678 (The Pile)

Max Activating Token Index: 647

Text #9

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7401. Min Act: -0.0000

Data Index: 1089165 (The Pile)

Max Activating Token Index: 120

Text #10

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8136. Min Act: -0.0000

Data Index: 1488107 (The Pile)

Max Activating Token Index: 61

Text #11

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7790. Min Act: -0.0000

Data Index: 599205 (The Pile)

Max Activating Token Index: 1006

Text #12

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7680. Min Act: -0.0000

Data Index: 331898 (The Pile)

Max Activating Token Index: 872

Text #13

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7113. Min Act: -0.0000

Data Index: 1952725 (The Pile)

Max Activating Token Index: 956

Text #14

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7347. Min Act: -0.0000

Data Index: 653896 (The Pile)

Max Activating Token Index: 540

Text #15

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7352. Min Act: -0.0000

Data Index: 639351 (The Pile)

Max Activating Token Index: 232

Text #16

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7804. Min Act: -0.0000

Data Index: 1173239 (The Pile)

Max Activating Token Index: 16

Text #17

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7636. Min Act: -0.0000

Data Index: 561793 (The Pile)

Max Activating Token Index: 1014

Text #18

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7303. Min Act: -0.0000

Data Index: 172547 (The Pile)

Max Activating Token Index: 300

Text #19

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7727. Min Act: -0.0000

Data Index: 313335 (The Pile)

Max Activating Token Index: 87