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

Dataset: The Pile

Neuron 3574 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.6734. Min Act: -0.0000

Data Index: 372457 (The Pile)

Max Activating Token Index: 266

Text #1

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.6020. Min Act: -0.0000

Data Index: 680673 (The Pile)

Max Activating Token Index: 942

Text #2

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.3461. Min Act: -0.0000

Data Index: 853928 (The Pile)

Max Activating Token Index: 343

Text #3

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.2342. Min Act: -0.0000

Data Index: 1611543 (The Pile)

Max Activating Token Index: 462

Text #4

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.3584. Min Act: -0.0000

Data Index: 1290098 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.2776. Min Act: -0.0000

Data Index: 415565 (The Pile)

Max Activating Token Index: 378

Text #6

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.4101. Min Act: -0.0000

Data Index: 1404806 (The Pile)

Max Activating Token Index: 1002

Text #7

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.1417. Min Act: -0.0000

Data Index: 1497601 (The Pile)

Max Activating Token Index: 86

Text #8

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.1022. Min Act: -0.0000

Data Index: 93471 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.2411. Min Act: -0.0000

Data Index: 859502 (The Pile)

Max Activating Token Index: 245

Text #10

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.0704. Min Act: -0.0000

Data Index: 945427 (The Pile)

Max Activating Token Index: 658

Text #11

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.0743. Min Act: -0.0000

Data Index: 69528 (The Pile)

Max Activating Token Index: 915

Text #12

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.1139. Min Act: -0.0000

Data Index: 183407 (The Pile)

Max Activating Token Index: 429

Text #13

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.1293. Min Act: -0.0000

Data Index: 1517003 (The Pile)

Max Activating Token Index: 452

Text #14

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.0934. Min Act: -0.0000

Data Index: 675206 (The Pile)

Max Activating Token Index: 681

Text #15

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.0728. Min Act: -0.0000

Data Index: 356379 (The Pile)

Max Activating Token Index: 435

Text #16

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.1455. Min Act: -0.0000

Data Index: 261282 (The Pile)

Max Activating Token Index: 606

Text #17

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.0981. Min Act: -0.0000

Data Index: 1736880 (The Pile)

Max Activating Token Index: 305

Text #18

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.0872. Min Act: -0.0000

Data Index: 540598 (The Pile)

Max Activating Token Index: 913

Text #19

Max Range: 1.6734. Min Range: -1.6734

Max Act: 1.0950. Min Act: -0.0000

Data Index: 12162 (The Pile)

Max Activating Token Index: 546