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

Dataset: The Pile

Neuron 311 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: 0.8821. Min Range: -0.8821

Max Act: 0.8821. Min Act: -0.0000

Data Index: 226820 (The Pile)

Max Activating Token Index: 804

Text #1

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8521. Min Act: -0.0000

Data Index: 473214 (The Pile)

Max Activating Token Index: 774

Text #2

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8158. Min Act: -0.0000

Data Index: 1094579 (The Pile)

Max Activating Token Index: 852

Text #3

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7658. Min Act: -0.0000

Data Index: 1726314 (The Pile)

Max Activating Token Index: 638

Text #4

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1620180 (The Pile)

Max Activating Token Index: 389

Text #5

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8396. Min Act: -0.0000

Data Index: 948118 (The Pile)

Max Activating Token Index: 574

Text #6

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8078. Min Act: -0.0000

Data Index: 42150 (The Pile)

Max Activating Token Index: 974

Text #7

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7762. Min Act: 0.0000

Data Index: 364223 (The Pile)

Max Activating Token Index: 194

Text #8

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7705. Min Act: -0.0000

Data Index: 628847 (The Pile)

Max Activating Token Index: 492

Text #9

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1718339 (The Pile)

Max Activating Token Index: 849

Text #10

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8258. Min Act: -0.0000

Data Index: 1275899 (The Pile)

Max Activating Token Index: 692

Text #11

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1633938 (The Pile)

Max Activating Token Index: 620

Text #12

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.8239. Min Act: -0.0000

Data Index: 825924 (The Pile)

Max Activating Token Index: 62

Text #13

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7815. Min Act: -0.0000

Data Index: 822246 (The Pile)

Max Activating Token Index: 835

Text #14

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1555358 (The Pile)

Max Activating Token Index: 652

Text #15

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7649. Min Act: -0.0000

Data Index: 265662 (The Pile)

Max Activating Token Index: 384

Text #16

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7119. Min Act: -0.0000

Data Index: 912412 (The Pile)

Max Activating Token Index: 448

Text #17

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1821988 (The Pile)

Max Activating Token Index: 806

Text #18

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7520. Min Act: -0.0000

Data Index: 1980728 (The Pile)

Max Activating Token Index: 322

Text #19

Max Range: 0.8821. Min Range: -0.8821

Max Act: 0.7883. Min Act: -0.0000

Data Index: 1670516 (The Pile)

Max Activating Token Index: 723