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

Dataset: The Pile

Neuron 2353 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: 1.3997. Min Range: -1.3997

Max Act: 1.3997. Min Act: -0.0000

Data Index: 937633 (The Pile)

Max Activating Token Index: 933

Text #1

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.1202. Min Act: -0.0000

Data Index: 1526486 (The Pile)

Max Activating Token Index: 608

Text #2

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.0972. Min Act: -0.0000

Data Index: 72624 (The Pile)

Max Activating Token Index: 386

Text #3

Max Range: 1.3997. Min Range: -1.3997

Max Act: 0.9609. Min Act: -0.0000

Data Index: 871574 (The Pile)

Max Activating Token Index: 92

Text #4

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.0140. Min Act: -0.0000

Data Index: 1493792 (The Pile)

Max Activating Token Index: 377

Text #5

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.0326. Min Act: -0.0000

Data Index: 136693 (The Pile)

Max Activating Token Index: 861

Text #6

Max Range: 1.3997. Min Range: -1.3997

Max Act: 0.8858. Min Act: -0.0000

Data Index: 1733395 (The Pile)

Max Activating Token Index: 727

Text #7

Max Range: 1.3997. Min Range: -1.3997

Max Act: 0.9935. Min Act: -0.0000

Data Index: 258344 (The Pile)

Max Activating Token Index: 888

Text #8

Max Range: 1.3997. Min Range: -1.3997

Max Act: 0.9255. Min Act: -0.0000

Data Index: 186544 (The Pile)

Max Activating Token Index: 867

Text #9

Max Range: 1.3997. Min Range: -1.3997

Max Act: 0.8974. Min Act: -0.0000

Data Index: 1536724 (The Pile)

Max Activating Token Index: 537

Text #10

Max Range: 1.3997. Min Range: -1.3997

Max Act: 0.8167. Min Act: -0.0000

Data Index: 1929803 (The Pile)

Max Activating Token Index: 666

Text #11

Max Range: 1.3997. Min Range: -1.3997

Max Act: 0.8641. Min Act: -0.0000

Data Index: 978045 (The Pile)

Max Activating Token Index: 369

Text #12

Max Range: 1.3997. Min Range: -1.3997

Max Act: 0.8442. Min Act: -0.0000

Data Index: 72565 (The Pile)

Max Activating Token Index: 30

Text #13

Max Range: 1.3997. Min Range: -1.3997

Max Act: 0.8857. Min Act: -0.0000

Data Index: 1523228 (The Pile)

Max Activating Token Index: 110

Text #14

Max Range: 1.3997. Min Range: -1.3997

Max Act: 0.8145. Min Act: -0.0000

Data Index: 1179690 (The Pile)

Max Activating Token Index: 912

Text #15

Max Range: 1.3997. Min Range: -1.3997

Max Act: 0.8296. Min Act: -0.0000

Data Index: 601068 (The Pile)

Max Activating Token Index: 823

Text #16

Max Range: 1.3997. Min Range: -1.3997

Max Act: 0.8491. Min Act: -0.0000

Data Index: 233601 (The Pile)

Max Activating Token Index: 871

Text #17

Max Range: 1.3997. Min Range: -1.3997

Max Act: 0.8481. Min Act: -0.0000

Data Index: 1117113 (The Pile)

Max Activating Token Index: 461

Text #18

Max Range: 1.3997. Min Range: -1.3997

Max Act: 0.8069. Min Act: -0.0000

Data Index: 380881 (The Pile)

Max Activating Token Index: 441

Text #19

Max Range: 1.3997. Min Range: -1.3997

Max Act: 0.8729. Min Act: -0.0000

Data Index: 1731497 (The Pile)

Max Activating Token Index: 638