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

Dataset: The Pile

Neuron 3080 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0433. Min Range: -3.0433

Max Act: 3.0433. Min Act: -0.0000

Data Index: 86908 (The Pile)

Max Activating Token Index: 291

Text #1

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.8008. Min Act: -0.0000

Data Index: 596639 (The Pile)

Max Activating Token Index: 990

Text #2

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.5939. Min Act: -0.0000

Data Index: 993529 (The Pile)

Max Activating Token Index: 979

Text #3

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.4867. Min Act: -0.0000

Data Index: 331365 (The Pile)

Max Activating Token Index: 760

Text #4

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.3439. Min Act: -0.0000

Data Index: 602625 (The Pile)

Max Activating Token Index: 659

Text #5

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.6465. Min Act: -0.0000

Data Index: 451859 (The Pile)

Max Activating Token Index: 453

Text #6

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.3169. Min Act: -0.0000

Data Index: 493742 (The Pile)

Max Activating Token Index: 95

Text #7

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.4256. Min Act: -0.0000

Data Index: 819019 (The Pile)

Max Activating Token Index: 665

Text #8

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.4434. Min Act: -0.0000

Data Index: 453185 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.2767. Min Act: -0.0000

Data Index: 93560 (The Pile)

Max Activating Token Index: 650

Text #10

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.2664. Min Act: -0.0000

Data Index: 827605 (The Pile)

Max Activating Token Index: 1007

Text #11

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.2391. Min Act: -0.0000

Data Index: 123384 (The Pile)

Max Activating Token Index: 274

Text #12

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.3550. Min Act: -0.0000

Data Index: 790791 (The Pile)

Max Activating Token Index: 347

Text #13

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.3390. Min Act: -0.0000

Data Index: 616402 (The Pile)

Max Activating Token Index: 174

Text #14

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.4454. Min Act: -0.0000

Data Index: 1029108 (The Pile)

Max Activating Token Index: 898

Text #15

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.4626. Min Act: -0.0000

Data Index: 1510026 (The Pile)

Max Activating Token Index: 452

Text #16

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.4307. Min Act: -0.0000

Data Index: 1314809 (The Pile)

Max Activating Token Index: 330

Text #17

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.3213. Min Act: -0.0000

Data Index: 664428 (The Pile)

Max Activating Token Index: 745

Text #18

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.1957. Min Act: -0.0000

Data Index: 1899265 (The Pile)

Max Activating Token Index: 410

Text #19

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.1657. Min Act: -0.0000

Data Index: 1945441 (The Pile)

Max Activating Token Index: 49