Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1187 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.3716. Min Act: -0.0000

Data Index: 1142352 (The Pile)

Max Activating Token Index: 353

Text #1

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.3516. Min Act: -0.0000

Data Index: 423001 (The Pile)

Max Activating Token Index: 359

Text #2

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.2831. Min Act: -0.0000

Data Index: 900651 (The Pile)

Max Activating Token Index: 649

Text #3

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.2795. Min Act: -0.0000

Data Index: 1299804 (The Pile)

Max Activating Token Index: 1022

Text #4

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1992. Min Act: -0.0000

Data Index: 656922 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1989. Min Act: -0.0000

Data Index: 1648297 (The Pile)

Max Activating Token Index: 323

Text #6

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.2282. Min Act: -0.0000

Data Index: 808036 (The Pile)

Max Activating Token Index: 615

Text #7

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1887. Min Act: -0.0000

Data Index: 425704 (The Pile)

Max Activating Token Index: 380

Text #8

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1375. Min Act: -0.0000

Data Index: 444422 (The Pile)

Max Activating Token Index: 958

Text #9

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1431. Min Act: -0.0000

Data Index: 900383 (The Pile)

Max Activating Token Index: 558

Text #10

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1764. Min Act: -0.0000

Data Index: 1204726 (The Pile)

Max Activating Token Index: 192

Text #11

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1140. Min Act: -0.0000

Data Index: 1234829 (The Pile)

Max Activating Token Index: 908

Text #12

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1121. Min Act: -0.0000

Data Index: 1520133 (The Pile)

Max Activating Token Index: 744

Text #13

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0982. Min Act: -0.0000

Data Index: 1837557 (The Pile)

Max Activating Token Index: 389

Text #14

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0593. Min Act: -0.0000

Data Index: 1087469 (The Pile)

Max Activating Token Index: 275

Text #15

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0112. Min Act: -0.0000

Data Index: 298567 (The Pile)

Max Activating Token Index: 678

Text #16

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0640. Min Act: -0.0000

Data Index: 807682 (The Pile)

Max Activating Token Index: 630

Text #17

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1105. Min Act: -0.0000

Data Index: 312490 (The Pile)

Max Activating Token Index: 578

Text #18

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0533. Min Act: -0.0000

Data Index: 1192768 (The Pile)

Max Activating Token Index: 651

Text #19

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.9775. Min Act: -0.0000

Data Index: 1512620 (The Pile)

Max Activating Token Index: 924