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

Dataset: The Pile

Neuron 3313 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: 0.7565. Min Range: -0.7565

Max Act: 0.7311. Min Act: -0.0000

Data Index: 1114917 (The Pile)

Max Activating Token Index: 228

Text #1

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.7565. Min Act: -0.0000

Data Index: 410996 (The Pile)

Max Activating Token Index: 521

Text #2

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6348. Min Act: -0.0000

Data Index: 359400 (The Pile)

Max Activating Token Index: 526

Text #3

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1789328 (The Pile)

Max Activating Token Index: 501

Text #4

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6264. Min Act: -0.0000

Data Index: 484203 (The Pile)

Max Activating Token Index: 289

Text #5

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6277. Min Act: -0.0000

Data Index: 837030 (The Pile)

Max Activating Token Index: 520

Text #6

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6476. Min Act: -0.0000

Data Index: 423974 (The Pile)

Max Activating Token Index: 246

Text #7

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6328. Min Act: -0.0000

Data Index: 1159585 (The Pile)

Max Activating Token Index: 220

Text #8

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1413144 (The Pile)

Max Activating Token Index: 791

Text #9

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6055. Min Act: -0.0000

Data Index: 892699 (The Pile)

Max Activating Token Index: 259

Text #10

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6408. Min Act: -0.0000

Data Index: 601687 (The Pile)

Max Activating Token Index: 338

Text #11

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6357. Min Act: -0.0000

Data Index: 1458058 (The Pile)

Max Activating Token Index: 899

Text #12

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6769. Min Act: -0.0000

Data Index: 1410253 (The Pile)

Max Activating Token Index: 227

Text #13

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6162. Min Act: -0.0000

Data Index: 323748 (The Pile)

Max Activating Token Index: 619

Text #14

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.6487. Min Act: -0.0000

Data Index: 1245799 (The Pile)

Max Activating Token Index: 265

Text #15

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.5335. Min Act: -0.0000

Data Index: 604924 (The Pile)

Max Activating Token Index: 752

Text #16

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.5985. Min Act: -0.0000

Data Index: 1708432 (The Pile)

Max Activating Token Index: 963

Text #17

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.4925. Min Act: -0.0000

Data Index: 865033 (The Pile)

Max Activating Token Index: 50

Text #18

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.5416. Min Act: -0.0000

Data Index: 1409272 (The Pile)

Max Activating Token Index: 230

Text #19

Max Range: 0.7565. Min Range: -0.7565

Max Act: 0.4832. Min Act: -0.0000

Data Index: 133612 (The Pile)

Max Activating Token Index: 976