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

Dataset: The Pile

Neuron 1485 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.6241. Min Act: -0.0000

Data Index: 774849 (The Pile)

Max Activating Token Index: 749

Text #1

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.6156. Min Act: -0.0000

Data Index: 210505 (The Pile)

Max Activating Token Index: 477

Text #2

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5680. Min Act: -0.0000

Data Index: 699688 (The Pile)

Max Activating Token Index: 1010

Text #3

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5605. Min Act: -0.0000

Data Index: 1153835 (The Pile)

Max Activating Token Index: 418

Text #4

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1142004 (The Pile)

Max Activating Token Index: 744

Text #5

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5437. Min Act: -0.0000

Data Index: 839987 (The Pile)

Max Activating Token Index: 320

Text #6

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5062. Min Act: -0.0000

Data Index: 981992 (The Pile)

Max Activating Token Index: 796

Text #7

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1263577 (The Pile)

Max Activating Token Index: 999

Text #8

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4869. Min Act: -0.0000

Data Index: 667477 (The Pile)

Max Activating Token Index: 838

Text #9

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1124932 (The Pile)

Max Activating Token Index: 356

Text #10

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5403. Min Act: -0.0000

Data Index: 307724 (The Pile)

Max Activating Token Index: 125

Text #11

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4892. Min Act: -0.0000

Data Index: 555929 (The Pile)

Max Activating Token Index: 271

Text #12

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4865. Min Act: -0.0000

Data Index: 373434 (The Pile)

Max Activating Token Index: 309

Text #13

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1583833 (The Pile)

Max Activating Token Index: 102

Text #14

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5333. Min Act: -0.0000

Data Index: 897244 (The Pile)

Max Activating Token Index: 666

Text #15

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4836. Min Act: -0.0000

Data Index: 823756 (The Pile)

Max Activating Token Index: 543

Text #16

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1522651 (The Pile)

Max Activating Token Index: 223

Text #17

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4605. Min Act: -0.0000

Data Index: 362986 (The Pile)

Max Activating Token Index: 77

Text #18

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4835. Min Act: -0.0000

Data Index: 351522 (The Pile)

Max Activating Token Index: 553

Text #19

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1940860 (The Pile)

Max Activating Token Index: 149