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

Dataset: The Pile

Neuron 2367 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.7735. Min Act: -0.0000

Data Index: 1489213 (The Pile)

Max Activating Token Index: 424

Text #1

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.2988. Min Act: -0.0000

Data Index: 1624151 (The Pile)

Max Activating Token Index: 657

Text #2

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.3810. Min Act: -0.0000

Data Index: 453601 (The Pile)

Max Activating Token Index: 322

Text #3

Max Range: 3.7735. Min Range: -3.7735

Max Act: 3.2365. Min Act: -0.0000

Data Index: 9863 (The Pile)

Max Activating Token Index: 49

Text #4

Max Range: 3.7735. Min Range: -3.7735

Max Act: 2.8636. Min Act: -0.0000

Data Index: 856920 (The Pile)

Max Activating Token Index: 19

Text #5

Max Range: 3.7735. Min Range: -3.7735

Max Act: 2.7361. Min Act: -0.0000

Data Index: 1497970 (The Pile)

Max Activating Token Index: 387

Text #6

Max Range: 3.7735. Min Range: -3.7735

Max Act: 2.7144. Min Act: -0.0000

Data Index: 1248557 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 3.7735. Min Range: -3.7735

Max Act: 2.7868. Min Act: -0.0000

Data Index: 845966 (The Pile)

Max Activating Token Index: 96

Text #8

Max Range: 3.7735. Min Range: -3.7735

Max Act: 2.7362. Min Act: -0.0000

Data Index: 1794955 (The Pile)

Max Activating Token Index: 974

Text #9

Max Range: 3.7735. Min Range: -3.7735

Max Act: 2.2981. Min Act: -0.0000

Data Index: 999052 (The Pile)

Max Activating Token Index: 512

Text #10

Max Range: 3.7735. Min Range: -3.7735

Max Act: 2.7551. Min Act: -0.0000

Data Index: 788859 (The Pile)

Max Activating Token Index: 935

Text #11

Max Range: 3.7735. Min Range: -3.7735

Max Act: 2.4084. Min Act: -0.0000

Data Index: 1950829 (The Pile)

Max Activating Token Index: 834

Text #12

Max Range: 3.7735. Min Range: -3.7735

Max Act: 2.1363. Min Act: -0.0000

Data Index: 1147850 (The Pile)

Max Activating Token Index: 30

Text #13

Max Range: 3.7735. Min Range: -3.7735

Max Act: 2.4310. Min Act: -0.0000

Data Index: 1101096 (The Pile)

Max Activating Token Index: 787

Text #14

Max Range: 3.7735. Min Range: -3.7735

Max Act: 2.4288. Min Act: -0.0000

Data Index: 1823043 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 3.7735. Min Range: -3.7735

Max Act: 2.2348. Min Act: -0.0000

Data Index: 704744 (The Pile)

Max Activating Token Index: 338

Text #16

Max Range: 3.7735. Min Range: -3.7735

Max Act: 2.2454. Min Act: -0.0000

Data Index: 437844 (The Pile)

Max Activating Token Index: 384

Text #17

Max Range: 3.7735. Min Range: -3.7735

Max Act: 2.1079. Min Act: -0.0000

Data Index: 423561 (The Pile)

Max Activating Token Index: 308

Text #18

Max Range: 3.7735. Min Range: -3.7735

Max Act: 1.9574. Min Act: -0.0000

Data Index: 560417 (The Pile)

Max Activating Token Index: 167

Text #19

Max Range: 3.7735. Min Range: -3.7735

Max Act: 2.2915. Min Act: -0.0000

Data Index: 1303300 (The Pile)

Max Activating Token Index: 275