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

Dataset: The Pile

Neuron 2799 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.9965. Min Act: -0.0000

Data Index: 535920 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.9285. Min Act: -0.0000

Data Index: 1419925 (The Pile)

Max Activating Token Index: 680

Text #2

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.8208. Min Act: -0.0000

Data Index: 962742 (The Pile)

Max Activating Token Index: 931

Text #3

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.9050. Min Act: -0.0000

Data Index: 1042282 (The Pile)

Max Activating Token Index: 976

Text #4

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.7402. Min Act: -0.0000

Data Index: 557938 (The Pile)

Max Activating Token Index: 622

Text #5

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.9881. Min Act: -0.0000

Data Index: 1702243 (The Pile)

Max Activating Token Index: 682

Text #6

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.5473. Min Act: -0.0000

Data Index: 816203 (The Pile)

Max Activating Token Index: 340

Text #7

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.7155. Min Act: -0.0000

Data Index: 1056437 (The Pile)

Max Activating Token Index: 642

Text #8

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.6086. Min Act: -0.0000

Data Index: 927120 (The Pile)

Max Activating Token Index: 544

Text #9

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.6385. Min Act: -0.0000

Data Index: 1626783 (The Pile)

Max Activating Token Index: 925

Text #10

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.6321. Min Act: -0.0000

Data Index: 335785 (The Pile)

Max Activating Token Index: 101

Text #11

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.7142. Min Act: -0.0000

Data Index: 166126 (The Pile)

Max Activating Token Index: 694

Text #12

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.6394. Min Act: -0.0000

Data Index: 1326604 (The Pile)

Max Activating Token Index: 994

Text #13

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.6320. Min Act: -0.0000

Data Index: 1990468 (The Pile)

Max Activating Token Index: 115

Text #14

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.4731. Min Act: -0.0000

Data Index: 1025493 (The Pile)

Max Activating Token Index: 906

Text #15

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.3618. Min Act: -0.0000

Data Index: 361092 (The Pile)

Max Activating Token Index: 550

Text #16

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.6164. Min Act: -0.0000

Data Index: 231977 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.4921. Min Act: -0.0000

Data Index: 185014 (The Pile)

Max Activating Token Index: 573

Text #18

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.6255. Min Act: -0.0000

Data Index: 357536 (The Pile)

Max Activating Token Index: 33

Text #19

Max Range: 1.9965. Min Range: -1.9965

Max Act: 1.6232. Min Act: -0.0000

Data Index: 380823 (The Pile)

Max Activating Token Index: 520