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

Dataset: The Pile

Neuron 4760 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.1627. Min Act: -0.0000

Data Index: 646008 (The Pile)

Max Activating Token Index: 477

Text #1

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0958. Min Act: -0.0000

Data Index: 1891934 (The Pile)

Max Activating Token Index: 470

Text #2

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0154. Min Act: -0.0000

Data Index: 1007280 (The Pile)

Max Activating Token Index: 400

Text #3

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9586. Min Act: -0.0000

Data Index: 1815995 (The Pile)

Max Activating Token Index: 383

Text #4

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9466. Min Act: -0.0000

Data Index: 242819 (The Pile)

Max Activating Token Index: 253

Text #5

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9212. Min Act: -0.0000

Data Index: 5168 (The Pile)

Max Activating Token Index: 343

Text #6

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9465. Min Act: -0.0000

Data Index: 1386092 (The Pile)

Max Activating Token Index: 521

Text #7

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8765. Min Act: -0.0000

Data Index: 1794260 (The Pile)

Max Activating Token Index: 123

Text #8

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1732356 (The Pile)

Max Activating Token Index: 62

Text #9

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8922. Min Act: -0.0000

Data Index: 1482358 (The Pile)

Max Activating Token Index: 289

Text #10

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9367. Min Act: -0.0000

Data Index: 955988 (The Pile)

Max Activating Token Index: 946

Text #11

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9016. Min Act: -0.0000

Data Index: 1972254 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8904. Min Act: -0.0000

Data Index: 482643 (The Pile)

Max Activating Token Index: 497

Text #13

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8481. Min Act: -0.0000

Data Index: 1767567 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1928502 (The Pile)

Max Activating Token Index: 918

Text #15

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8833. Min Act: -0.0000

Data Index: 1069275 (The Pile)

Max Activating Token Index: 300

Text #16

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8315. Min Act: -0.0000

Data Index: 921220 (The Pile)

Max Activating Token Index: 786

Text #17

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8581. Min Act: -0.0000

Data Index: 165631 (The Pile)

Max Activating Token Index: 596

Text #18

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8470. Min Act: -0.0000

Data Index: 1172668 (The Pile)

Max Activating Token Index: 727

Text #19

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8095. Min Act: -0.0000

Data Index: 1945672 (The Pile)

Max Activating Token Index: 245