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

Dataset: The Pile

Neuron 527 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: 1.3809. Min Range: -1.3809

Max Act: 1.3475. Min Act: -0.0000

Data Index: 441404 (The Pile)

Max Activating Token Index: 91

Text #1

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.3809. Min Act: -0.0000

Data Index: 681000 (The Pile)

Max Activating Token Index: 179

Text #2

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.2903. Min Act: -0.0000

Data Index: 1043809 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.3373. Min Act: -0.0000

Data Index: 594217 (The Pile)

Max Activating Token Index: 920

Text #4

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.1487. Min Act: -0.0000

Data Index: 860873 (The Pile)

Max Activating Token Index: 841

Text #5

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.2061. Min Act: -0.0000

Data Index: 1065304 (The Pile)

Max Activating Token Index: 398

Text #6

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.1700. Min Act: -0.0000

Data Index: 1606002 (The Pile)

Max Activating Token Index: 443

Text #7

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.1524. Min Act: -0.0000

Data Index: 815414 (The Pile)

Max Activating Token Index: 200

Text #8

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.0644. Min Act: -0.0000

Data Index: 807542 (The Pile)

Max Activating Token Index: 678

Text #9

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.1272. Min Act: -0.0000

Data Index: 902345 (The Pile)

Max Activating Token Index: 150

Text #10

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.1190. Min Act: 0.0000

Data Index: 831333 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1122087 (The Pile)

Max Activating Token Index: 999

Text #12

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.1738. Min Act: -0.0000

Data Index: 739250 (The Pile)

Max Activating Token Index: 49

Text #13

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.1274. Min Act: -0.0000

Data Index: 784744 (The Pile)

Max Activating Token Index: 680

Text #14

Max Range: 1.3809. Min Range: -1.3809

Max Act: 0.9970. Min Act: -0.0000

Data Index: 121431 (The Pile)

Max Activating Token Index: 788

Text #15

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.0481. Min Act: -0.0000

Data Index: 1681583 (The Pile)

Max Activating Token Index: 549

Text #16

Max Range: 1.3809. Min Range: -1.3809

Max Act: 0.9810. Min Act: -0.0000

Data Index: 1858599 (The Pile)

Max Activating Token Index: 1016

Text #17

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.0253. Min Act: -0.0000

Data Index: 357510 (The Pile)

Max Activating Token Index: 533

Text #18

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.0043. Min Act: -0.0000

Data Index: 69376 (The Pile)

Max Activating Token Index: 112

Text #19

Max Range: 1.3809. Min Range: -1.3809

Max Act: 1.0684. Min Act: -0.0000

Data Index: 900587 (The Pile)

Max Activating Token Index: 453