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

Dataset: The Pile

Neuron 3131 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.9330. Min Act: -0.0000

Data Index: 1456459 (The Pile)

Max Activating Token Index: 434

Text #1

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.7521. Min Act: -0.0000

Data Index: 613385 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.7682. Min Act: -0.0000

Data Index: 55006 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1981215 (The Pile)

Max Activating Token Index: 999

Text #4

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1874924 (The Pile)

Max Activating Token Index: 1007

Text #5

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6763. Min Act: -0.0000

Data Index: 1214861 (The Pile)

Max Activating Token Index: 459

Text #6

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6804. Min Act: -0.0000

Data Index: 749632 (The Pile)

Max Activating Token Index: 321

Text #7

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6564. Min Act: 0.0001

Data Index: 1190920 (The Pile)

Max Activating Token Index: 1007

Text #8

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6709. Min Act: 0.0001

Data Index: 1970666 (The Pile)

Max Activating Token Index: 1000

Text #9

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6403. Min Act: -0.0000

Data Index: 6392 (The Pile)

Max Activating Token Index: 357

Text #10

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6431. Min Act: -0.0000

Data Index: 746055 (The Pile)

Max Activating Token Index: 94

Text #11

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6350. Min Act: 0.0000

Data Index: 971090 (The Pile)

Max Activating Token Index: 682

Text #12

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6557. Min Act: -0.0000

Data Index: 661737 (The Pile)

Max Activating Token Index: 947

Text #13

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.5829. Min Act: -0.0000

Data Index: 1757994 (The Pile)

Max Activating Token Index: 1012

Text #14

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6221. Min Act: -0.0000

Data Index: 1049152 (The Pile)

Max Activating Token Index: 313

Text #15

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.5438. Min Act: -0.0000

Data Index: 754496 (The Pile)

Max Activating Token Index: 62

Text #16

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.5965. Min Act: 0.0000

Data Index: 427314 (The Pile)

Max Activating Token Index: 354

Text #17

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6134. Min Act: -0.0000

Data Index: 383937 (The Pile)

Max Activating Token Index: 392

Text #18

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.6066. Min Act: -0.0000

Data Index: 941083 (The Pile)

Max Activating Token Index: 227

Text #19

Max Range: 0.9330. Min Range: -0.9330

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1972836 (The Pile)

Max Activating Token Index: 449