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

Dataset: The Pile

Neuron 3445 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: 0.8330. Min Range: -0.8330

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1904302 (The Pile)

Max Activating Token Index: 913

Text #1

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.8330. Min Act: -0.0000

Data Index: 951362 (The Pile)

Max Activating Token Index: 219

Text #2

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6821. Min Act: -0.0000

Data Index: 367246 (The Pile)

Max Activating Token Index: 551

Text #3

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1591860 (The Pile)

Max Activating Token Index: 472

Text #4

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1048136 (The Pile)

Max Activating Token Index: 665

Text #5

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6142. Min Act: -0.0000

Data Index: 1754875 (The Pile)

Max Activating Token Index: 28

Text #6

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6107. Min Act: -0.0000

Data Index: 544471 (The Pile)

Max Activating Token Index: 331

Text #7

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6042. Min Act: -0.0000

Data Index: 1422514 (The Pile)

Max Activating Token Index: 633

Text #8

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5788. Min Act: -0.0000

Data Index: 480971 (The Pile)

Max Activating Token Index: 384

Text #9

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6066. Min Act: -0.0000

Data Index: 839621 (The Pile)

Max Activating Token Index: 679

Text #10

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5293. Min Act: -0.0000

Data Index: 687310 (The Pile)

Max Activating Token Index: 395

Text #11

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5816. Min Act: -0.0000

Data Index: 618273 (The Pile)

Max Activating Token Index: 257

Text #12

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1703807 (The Pile)

Max Activating Token Index: 6

Text #13

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1679781 (The Pile)

Max Activating Token Index: 778

Text #14

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5678. Min Act: -0.0000

Data Index: 821487 (The Pile)

Max Activating Token Index: 1019

Text #15

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1517061 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5837. Min Act: -0.0000

Data Index: 517264 (The Pile)

Max Activating Token Index: 818

Text #17

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1904972 (The Pile)

Max Activating Token Index: 228

Text #18

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5699. Min Act: -0.0000

Data Index: 578690 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1856027 (The Pile)

Max Activating Token Index: 369