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

Dataset: The Pile

Neuron 2208 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.5471. Min Act: -0.0000

Data Index: 1934633 (The Pile)

Max Activating Token Index: 415

Text #1

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.4948. Min Act: -0.0000

Data Index: 503021 (The Pile)

Max Activating Token Index: 281

Text #2

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3541. Min Act: -0.0000

Data Index: 23599 (The Pile)

Max Activating Token Index: 205

Text #3

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.4062. Min Act: -0.0000

Data Index: 857284 (The Pile)

Max Activating Token Index: 228

Text #4

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3109. Min Act: -0.0000

Data Index: 95818 (The Pile)

Max Activating Token Index: 220

Text #5

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.4665. Min Act: -0.0000

Data Index: 287151 (The Pile)

Max Activating Token Index: 358

Text #6

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3691. Min Act: -0.0000

Data Index: 1855152 (The Pile)

Max Activating Token Index: 760

Text #7

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3406. Min Act: -0.0000

Data Index: 1533017 (The Pile)

Max Activating Token Index: 274

Text #8

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3134. Min Act: -0.0000

Data Index: 302142 (The Pile)

Max Activating Token Index: 179

Text #9

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3210. Min Act: -0.0000

Data Index: 690857 (The Pile)

Max Activating Token Index: 132

Text #10

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.2406. Min Act: -0.0000

Data Index: 124316 (The Pile)

Max Activating Token Index: 545

Text #11

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3911. Min Act: -0.0000

Data Index: 1025693 (The Pile)

Max Activating Token Index: 671

Text #12

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.2585. Min Act: -0.0000

Data Index: 1801373 (The Pile)

Max Activating Token Index: 739

Text #13

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.2913. Min Act: -0.0000

Data Index: 307688 (The Pile)

Max Activating Token Index: 275

Text #14

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.1900. Min Act: -0.0000

Data Index: 1489041 (The Pile)

Max Activating Token Index: 934

Text #15

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.1795. Min Act: -0.0000

Data Index: 1301795 (The Pile)

Max Activating Token Index: 323

Text #16

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.1815. Min Act: -0.0000

Data Index: 996015 (The Pile)

Max Activating Token Index: 646

Text #17

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.2780. Min Act: -0.0000

Data Index: 1174600 (The Pile)

Max Activating Token Index: 510

Text #18

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.2020. Min Act: -0.0000

Data Index: 752356 (The Pile)

Max Activating Token Index: 515

Text #19

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3058. Min Act: -0.0000

Data Index: 1662691 (The Pile)

Max Activating Token Index: 651