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

Dataset: The Pile

Neuron 2683 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: 0.1913. Min Range: -0.1913

Max Act: 0.1882. Min Act: -0.0000

Data Index: 29879 (The Pile)

Max Activating Token Index: 782

Text #1

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1913. Min Act: 0.0000

Data Index: 1752884 (The Pile)

Max Activating Token Index: 228

Text #2

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1780. Min Act: -0.0000

Data Index: 832211 (The Pile)

Max Activating Token Index: 501

Text #3

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1796. Min Act: -0.0000

Data Index: 620307 (The Pile)

Max Activating Token Index: 777

Text #4

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1606. Min Act: -0.0000

Data Index: 748519 (The Pile)

Max Activating Token Index: 372

Text #5

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1299185 (The Pile)

Max Activating Token Index: 623

Text #6

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1505. Min Act: -0.0000

Data Index: 1492395 (The Pile)

Max Activating Token Index: 270

Text #7

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1510. Min Act: 0.0000

Data Index: 1517329 (The Pile)

Max Activating Token Index: 528

Text #8

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1526. Min Act: 0.0000

Data Index: 1214953 (The Pile)

Max Activating Token Index: 438

Text #9

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1512. Min Act: 0.0000

Data Index: 684153 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1515235 (The Pile)

Max Activating Token Index: 749

Text #11

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1301. Min Act: -0.0000

Data Index: 545567 (The Pile)

Max Activating Token Index: 395

Text #12

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1396. Min Act: -0.0000

Data Index: 1137661 (The Pile)

Max Activating Token Index: 410

Text #13

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1366. Min Act: -0.0000

Data Index: 1553548 (The Pile)

Max Activating Token Index: 310

Text #14

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1357. Min Act: -0.0000

Data Index: 30306 (The Pile)

Max Activating Token Index: 754

Text #15

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1845229 (The Pile)

Max Activating Token Index: 316

Text #16

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1263. Min Act: -0.0000

Data Index: 794778 (The Pile)

Max Activating Token Index: 445

Text #17

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1349. Min Act: -0.0000

Data Index: 262621 (The Pile)

Max Activating Token Index: 653

Text #18

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1864084 (The Pile)

Max Activating Token Index: 62

Text #19

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1183. Min Act: -0.0000

Data Index: 315509 (The Pile)

Max Activating Token Index: 470