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

Dataset: The Pile

Neuron 762 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: 0.8574. Min Range: -0.8574

Max Act: 0.7159. Min Act: -0.0000

Data Index: 216273 (The Pile)

Max Activating Token Index: 216

Text #1

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.8409. Min Act: -0.0000

Data Index: 844827 (The Pile)

Max Activating Token Index: 750

Text #2

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.8190. Min Act: -0.0000

Data Index: 1621438 (The Pile)

Max Activating Token Index: 394

Text #3

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.8574. Min Act: -0.0000

Data Index: 748853 (The Pile)

Max Activating Token Index: 218

Text #4

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.8558. Min Act: -0.0000

Data Index: 696180 (The Pile)

Max Activating Token Index: 778

Text #5

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.8092. Min Act: -0.0000

Data Index: 629117 (The Pile)

Max Activating Token Index: 488

Text #6

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1676614 (The Pile)

Max Activating Token Index: 483

Text #7

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1252741 (The Pile)

Max Activating Token Index: 111

Text #8

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7433. Min Act: -0.0000

Data Index: 904428 (The Pile)

Max Activating Token Index: 520

Text #9

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1452033 (The Pile)

Max Activating Token Index: 750

Text #10

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7375. Min Act: -0.0000

Data Index: 1763209 (The Pile)

Max Activating Token Index: 74

Text #11

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1636229 (The Pile)

Max Activating Token Index: 734

Text #12

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7098. Min Act: -0.0000

Data Index: 621348 (The Pile)

Max Activating Token Index: 366

Text #13

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.6899. Min Act: -0.0000

Data Index: 297842 (The Pile)

Max Activating Token Index: 847

Text #14

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7349. Min Act: -0.0000

Data Index: 1275383 (The Pile)

Max Activating Token Index: 43

Text #15

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7367. Min Act: -0.0000

Data Index: 686930 (The Pile)

Max Activating Token Index: 462

Text #16

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.6719. Min Act: -0.0000

Data Index: 1992848 (The Pile)

Max Activating Token Index: 225

Text #17

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.6982. Min Act: -0.0000

Data Index: 974110 (The Pile)

Max Activating Token Index: 244

Text #18

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.6455. Min Act: -0.0000

Data Index: 1361026 (The Pile)

Max Activating Token Index: 179

Text #19

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1653989 (The Pile)

Max Activating Token Index: 803