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

Dataset: The Pile

Neuron 2092 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: 0.5658. Min Range: -0.5658

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1332816 (The Pile)

Max Activating Token Index: 582

Text #1

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4559. Min Act: -0.0000

Data Index: 326969 (The Pile)

Max Activating Token Index: 770

Text #2

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4471. Min Act: -0.0000

Data Index: 16316 (The Pile)

Max Activating Token Index: 938

Text #3

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4529. Min Act: -0.0000

Data Index: 250304 (The Pile)

Max Activating Token Index: 373

Text #4

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4110. Min Act: -0.0000

Data Index: 480563 (The Pile)

Max Activating Token Index: 159

Text #5

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3921. Min Act: -0.0000

Data Index: 965443 (The Pile)

Max Activating Token Index: 407

Text #6

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3883. Min Act: -0.0000

Data Index: 953437 (The Pile)

Max Activating Token Index: 776

Text #7

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3987. Min Act: -0.0000

Data Index: 1455572 (The Pile)

Max Activating Token Index: 60

Text #8

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3970. Min Act: -0.0000

Data Index: 351690 (The Pile)

Max Activating Token Index: 262

Text #9

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1039829 (The Pile)

Max Activating Token Index: 395

Text #10

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3870. Min Act: -0.0000

Data Index: 1416459 (The Pile)

Max Activating Token Index: 187

Text #11

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1179355 (The Pile)

Max Activating Token Index: 249

Text #12

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3712. Min Act: -0.0000

Data Index: 1789456 (The Pile)

Max Activating Token Index: 467

Text #13

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3797. Min Act: -0.0000

Data Index: 115294 (The Pile)

Max Activating Token Index: 548

Text #14

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3739. Min Act: -0.0000

Data Index: 1343470 (The Pile)

Max Activating Token Index: 744

Text #15

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3774. Min Act: -0.0000

Data Index: 673786 (The Pile)

Max Activating Token Index: 341

Text #16

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3502. Min Act: -0.0000

Data Index: 186277 (The Pile)

Max Activating Token Index: 323

Text #17

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3148. Min Act: -0.0000

Data Index: 254572 (The Pile)

Max Activating Token Index: 910

Text #18

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3650. Min Act: -0.0000

Data Index: 609626 (The Pile)

Max Activating Token Index: 639

Text #19

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.3394. Min Act: -0.0000

Data Index: 527727 (The Pile)

Max Activating Token Index: 564