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

Dataset: The Pile

Neuron 1736 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: 1.6650. Min Range: -1.6650

Max Act: 1.6650. Min Act: -0.0000

Data Index: 682683 (The Pile)

Max Activating Token Index: 424

Text #1

Max Range: 1.6650. Min Range: -1.6650

Max Act: 1.6220. Min Act: -0.0000

Data Index: 480003 (The Pile)

Max Activating Token Index: 29

Text #2

Max Range: 1.6650. Min Range: -1.6650

Max Act: 1.4255. Min Act: -0.0000

Data Index: 1395305 (The Pile)

Max Activating Token Index: 62

Text #3

Max Range: 1.6650. Min Range: -1.6650

Max Act: 1.3783. Min Act: -0.0000

Data Index: 842920 (The Pile)

Max Activating Token Index: 235

Text #4

Max Range: 1.6650. Min Range: -1.6650

Max Act: 1.4503. Min Act: -0.0000

Data Index: 831410 (The Pile)

Max Activating Token Index: 704

Text #5

Max Range: 1.6650. Min Range: -1.6650

Max Act: 1.6067. Min Act: -0.0000

Data Index: 1660342 (The Pile)

Max Activating Token Index: 661

Text #6

Max Range: 1.6650. Min Range: -1.6650

Max Act: 1.3903. Min Act: -0.0000

Data Index: 1092002 (The Pile)

Max Activating Token Index: 323

Text #7

Max Range: 1.6650. Min Range: -1.6650

Max Act: 1.3540. Min Act: -0.0000

Data Index: 1259087 (The Pile)

Max Activating Token Index: 360

Text #8

Max Range: 1.6650. Min Range: -1.6650

Max Act: 1.2876. Min Act: -0.0000

Data Index: 1602021 (The Pile)

Max Activating Token Index: 676

Text #9

Max Range: 1.6650. Min Range: -1.6650

Max Act: 1.3301. Min Act: -0.0000

Data Index: 796768 (The Pile)

Max Activating Token Index: 223

Text #10

Max Range: 1.6650. Min Range: -1.6650

Max Act: 1.3385. Min Act: -0.0000

Data Index: 496139 (The Pile)

Max Activating Token Index: 207

Text #11

Max Range: 1.6650. Min Range: -1.6650

Max Act: 1.4093. Min Act: -0.0000

Data Index: 1306199 (The Pile)

Max Activating Token Index: 127

Text #12

Max Range: 1.6650. Min Range: -1.6650

Max Act: 1.3129. Min Act: -0.0000

Data Index: 806641 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 1.6650. Min Range: -1.6650

Max Act: 1.2246. Min Act: -0.0000

Data Index: 1880789 (The Pile)

Max Activating Token Index: 953

Text #14

Max Range: 1.6650. Min Range: -1.6650

Max Act: 1.3299. Min Act: -0.0000

Data Index: 215032 (The Pile)

Max Activating Token Index: 497

Text #15

Max Range: 1.6650. Min Range: -1.6650

Max Act: 1.3454. Min Act: -0.0000

Data Index: 917175 (The Pile)

Max Activating Token Index: 815

Text #16

Max Range: 1.6650. Min Range: -1.6650

Max Act: 1.3477. Min Act: -0.0000

Data Index: 549816 (The Pile)

Max Activating Token Index: 15

Text #17

Max Range: 1.6650. Min Range: -1.6650

Max Act: 1.5792. Min Act: -0.0000

Data Index: 74794 (The Pile)

Max Activating Token Index: 76

Text #18

Max Range: 1.6650. Min Range: -1.6650

Max Act: 1.3085. Min Act: -0.0000

Data Index: 749008 (The Pile)

Max Activating Token Index: 482

Text #19

Max Range: 1.6650. Min Range: -1.6650

Max Act: 1.2684. Min Act: -0.0000

Data Index: 767056 (The Pile)

Max Activating Token Index: 377