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

Dataset: The Pile

Neuron 445 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: 1.0340. Min Range: -1.0340

Max Act: 1.0340. Min Act: -0.0000

Data Index: 862723 (The Pile)

Max Activating Token Index: 271

Text #1

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7648. Min Act: -0.0000

Data Index: 229192 (The Pile)

Max Activating Token Index: 842

Text #2

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8763. Min Act: -0.0000

Data Index: 1202083 (The Pile)

Max Activating Token Index: 220

Text #3

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7935. Min Act: -0.0000

Data Index: 233947 (The Pile)

Max Activating Token Index: 987

Text #4

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7635. Min Act: -0.0000

Data Index: 180165 (The Pile)

Max Activating Token Index: 969

Text #5

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7205. Min Act: -0.0000

Data Index: 1722550 (The Pile)

Max Activating Token Index: 768

Text #6

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1865633 (The Pile)

Max Activating Token Index: 842

Text #7

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.6284. Min Act: -0.0000

Data Index: 749913 (The Pile)

Max Activating Token Index: 563

Text #8

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.6539. Min Act: -0.0000

Data Index: 513666 (The Pile)

Max Activating Token Index: 971

Text #9

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1977264 (The Pile)

Max Activating Token Index: 903

Text #10

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.6805. Min Act: -0.0000

Data Index: 616507 (The Pile)

Max Activating Token Index: 655

Text #11

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.6828. Min Act: -0.0000

Data Index: 855638 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1722802 (The Pile)

Max Activating Token Index: 368

Text #13

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7174. Min Act: -0.0000

Data Index: 1090046 (The Pile)

Max Activating Token Index: 167

Text #14

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.6479. Min Act: -0.0000

Data Index: 7240 (The Pile)

Max Activating Token Index: 438

Text #15

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1874348 (The Pile)

Max Activating Token Index: 921

Text #16

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.6349. Min Act: -0.0000

Data Index: 253581 (The Pile)

Max Activating Token Index: 927

Text #17

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.6296. Min Act: -0.0000

Data Index: 1146640 (The Pile)

Max Activating Token Index: 482

Text #18

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.6270. Min Act: -0.0000

Data Index: 681119 (The Pile)

Max Activating Token Index: 615

Text #19

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.5277. Min Act: -0.0000

Data Index: 424728 (The Pile)

Max Activating Token Index: 705