Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 640 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 7.7421. Min Range: -7.7421

Max Act: 7.7421. Min Act: -0.0000

Data Index: 1868477 (The Pile)

Max Activating Token Index: 735

Text #1

Max Range: 7.7421. Min Range: -7.7421

Max Act: 7.6249. Min Act: -0.0000

Data Index: 1675156 (The Pile)

Max Activating Token Index: 11

Text #2

Max Range: 7.7421. Min Range: -7.7421

Max Act: 7.3589. Min Act: -0.0000

Data Index: 518548 (The Pile)

Max Activating Token Index: 14

Text #3

Max Range: 7.7421. Min Range: -7.7421

Max Act: 7.0961. Min Act: -0.0000

Data Index: 1658377 (The Pile)

Max Activating Token Index: 146

Text #4

Max Range: 7.7421. Min Range: -7.7421

Max Act: 7.3920. Min Act: -0.0000

Data Index: 1572191 (The Pile)

Max Activating Token Index: 469

Text #5

Max Range: 7.7421. Min Range: -7.7421

Max Act: 7.3636. Min Act: -0.0000

Data Index: 987603 (The Pile)

Max Activating Token Index: 12

Text #6

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.9529. Min Act: -0.0000

Data Index: 500642 (The Pile)

Max Activating Token Index: 67

Text #7

Max Range: 7.7421. Min Range: -7.7421

Max Act: 7.1251. Min Act: -0.0000

Data Index: 542187 (The Pile)

Max Activating Token Index: 10

Text #8

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.9091. Min Act: -0.0000

Data Index: 1960483 (The Pile)

Max Activating Token Index: 354

Text #9

Max Range: 7.7421. Min Range: -7.7421

Max Act: 7.0308. Min Act: -0.0000

Data Index: 71661 (The Pile)

Max Activating Token Index: 13

Text #10

Max Range: 7.7421. Min Range: -7.7421

Max Act: 7.1463. Min Act: -0.0000

Data Index: 283756 (The Pile)

Max Activating Token Index: 21

Text #11

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.9347. Min Act: -0.0000

Data Index: 1704407 (The Pile)

Max Activating Token Index: 17

Text #12

Max Range: 7.7421. Min Range: -7.7421

Max Act: 7.1328. Min Act: -0.0000

Data Index: 1040662 (The Pile)

Max Activating Token Index: 156

Text #13

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.4963. Min Act: -0.0000

Data Index: 1602453 (The Pile)

Max Activating Token Index: 20

Text #14

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.9897. Min Act: -0.0000

Data Index: 211660 (The Pile)

Max Activating Token Index: 20

Text #15

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.6190. Min Act: -0.0000

Data Index: 1082559 (The Pile)

Max Activating Token Index: 18

Text #16

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.7639. Min Act: -0.0000

Data Index: 117008 (The Pile)

Max Activating Token Index: 16

Text #17

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.3939. Min Act: -0.0000

Data Index: 579437 (The Pile)

Max Activating Token Index: 21

Text #18

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.9210. Min Act: -0.0000

Data Index: 318605 (The Pile)

Max Activating Token Index: 27

Text #19

Max Range: 7.7421. Min Range: -7.7421

Max Act: 6.7267. Min Act: -0.0000

Data Index: 492692 (The Pile)

Max Activating Token Index: 15