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

Dataset: The Pile

Neuron 4801 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.8491. Min Act: -0.0000

Data Index: 1395208 (The Pile)

Max Activating Token Index: 372

Text #1

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.7451. Min Act: -0.0000

Data Index: 1782261 (The Pile)

Max Activating Token Index: 251

Text #2

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.7174. Min Act: -0.0000

Data Index: 848673 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.9791. Min Act: -0.0000

Data Index: 11927 (The Pile)

Max Activating Token Index: 402

Text #4

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.6893. Min Act: -0.0000

Data Index: 882156 (The Pile)

Max Activating Token Index: 806

Text #5

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.7539. Min Act: -0.0000

Data Index: 1239530 (The Pile)

Max Activating Token Index: 285

Text #6

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.6237. Min Act: -0.0000

Data Index: 1020522 (The Pile)

Max Activating Token Index: 766

Text #7

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.6098. Min Act: -0.0000

Data Index: 13347 (The Pile)

Max Activating Token Index: 116

Text #8

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.6082. Min Act: -0.0000

Data Index: 1009367 (The Pile)

Max Activating Token Index: 709

Text #9

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.6725. Min Act: -0.0000

Data Index: 510584 (The Pile)

Max Activating Token Index: 668

Text #10

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.6685. Min Act: -0.0000

Data Index: 1471717 (The Pile)

Max Activating Token Index: 558

Text #11

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.3216. Min Act: -0.0000

Data Index: 687944 (The Pile)

Max Activating Token Index: 670

Text #12

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.3186. Min Act: -0.0000

Data Index: 454455 (The Pile)

Max Activating Token Index: 899

Text #13

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.6152. Min Act: -0.0000

Data Index: 629710 (The Pile)

Max Activating Token Index: 652

Text #14

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.5930. Min Act: -0.0000

Data Index: 395551 (The Pile)

Max Activating Token Index: 342

Text #15

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.5597. Min Act: -0.0000

Data Index: 1049380 (The Pile)

Max Activating Token Index: 338

Text #16

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.4047. Min Act: -0.0000

Data Index: 1430479 (The Pile)

Max Activating Token Index: 740

Text #17

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.4371. Min Act: -0.0000

Data Index: 639167 (The Pile)

Max Activating Token Index: 926

Text #18

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.3824. Min Act: -0.0000

Data Index: 1165137 (The Pile)

Max Activating Token Index: 508

Text #19

Max Range: 1.9791. Min Range: -1.9791

Max Act: 1.7158. Min Act: -0.0000

Data Index: 305490 (The Pile)

Max Activating Token Index: 798