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

Dataset: The Pile

Neuron 3806 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: 0.9423. Min Range: -0.9423

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1413554 (The Pile)

Max Activating Token Index: 381

Text #1

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7623. Min Act: -0.0000

Data Index: 486195 (The Pile)

Max Activating Token Index: 822

Text #2

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.8648. Min Act: -0.0000

Data Index: 999652 (The Pile)

Max Activating Token Index: 136

Text #3

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.9037. Min Act: 0.0000

Data Index: 1137819 (The Pile)

Max Activating Token Index: 929

Text #4

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1893439 (The Pile)

Max Activating Token Index: 390

Text #5

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.8865. Min Act: -0.0000

Data Index: 1154920 (The Pile)

Max Activating Token Index: 803

Text #6

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7892. Min Act: -0.0000

Data Index: 1748348 (The Pile)

Max Activating Token Index: 893

Text #7

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7660. Min Act: -0.0000

Data Index: 247237 (The Pile)

Max Activating Token Index: 58

Text #8

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7594. Min Act: -0.0000

Data Index: 1197296 (The Pile)

Max Activating Token Index: 587

Text #9

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7725. Min Act: -0.0000

Data Index: 723288 (The Pile)

Max Activating Token Index: 437

Text #10

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7408. Min Act: -0.0000

Data Index: 1000931 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.8079. Min Act: -0.0000

Data Index: 1956401 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1462371 (The Pile)

Max Activating Token Index: 383

Text #13

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7632. Min Act: -0.0000

Data Index: 607383 (The Pile)

Max Activating Token Index: 345

Text #14

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1781784 (The Pile)

Max Activating Token Index: 199

Text #15

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.8302. Min Act: -0.0000

Data Index: 1709681 (The Pile)

Max Activating Token Index: 817

Text #16

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7120. Min Act: -0.0000

Data Index: 490220 (The Pile)

Max Activating Token Index: 572

Text #17

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7254. Min Act: -0.0000

Data Index: 534182 (The Pile)

Max Activating Token Index: 334

Text #18

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.6982. Min Act: -0.0000

Data Index: 44121 (The Pile)

Max Activating Token Index: 999

Text #19

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.8089. Min Act: -0.0000

Data Index: 1534491 (The Pile)

Max Activating Token Index: 797