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

Dataset: The Pile

Neuron 2214 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: 0.8512. Min Range: -0.8512

Max Act: 0.8060. Min Act: -0.0000

Data Index: 605453 (The Pile)

Max Activating Token Index: 759

Text #1

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.8512. Min Act: -0.0000

Data Index: 1291627 (The Pile)

Max Activating Token Index: 839

Text #2

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.7475. Min Act: -0.0000

Data Index: 472152 (The Pile)

Max Activating Token Index: 385

Text #3

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1944859 (The Pile)

Max Activating Token Index: 405

Text #4

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1108152 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.7412. Min Act: -0.0000

Data Index: 1557701 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6606. Min Act: -0.0000

Data Index: 923793 (The Pile)

Max Activating Token Index: 219

Text #7

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6958. Min Act: 0.0000

Data Index: 1093904 (The Pile)

Max Activating Token Index: 819

Text #8

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6843. Min Act: -0.0000

Data Index: 759511 (The Pile)

Max Activating Token Index: 210

Text #9

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6481. Min Act: -0.0000

Data Index: 1745336 (The Pile)

Max Activating Token Index: 849

Text #10

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1284159 (The Pile)

Max Activating Token Index: 759

Text #11

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6401. Min Act: -0.0000

Data Index: 1721168 (The Pile)

Max Activating Token Index: 281

Text #12

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6571. Min Act: -0.0000

Data Index: 992308 (The Pile)

Max Activating Token Index: 438

Text #13

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6948. Min Act: -0.0000

Data Index: 721996 (The Pile)

Max Activating Token Index: 965

Text #14

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.7296. Min Act: 0.0000

Data Index: 1365735 (The Pile)

Max Activating Token Index: 589

Text #15

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.5775. Min Act: -0.0000

Data Index: 251855 (The Pile)

Max Activating Token Index: 422

Text #16

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1284196 (The Pile)

Max Activating Token Index: 488

Text #17

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1387277 (The Pile)

Max Activating Token Index: 161

Text #18

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6561. Min Act: -0.0000

Data Index: 810010 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 0.8512. Min Range: -0.8512

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1691888 (The Pile)

Max Activating Token Index: 878