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

Dataset: The Pile

Neuron 2012 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0525. Min Range: -1.0525

Max Act: 1.0525. Min Act: -0.0000

Data Index: 266539 (The Pile)

Max Activating Token Index: 797

Text #1

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.9362. Min Act: -0.0000

Data Index: 1015351 (The Pile)

Max Activating Token Index: 352

Text #2

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.9201. Min Act: -0.0000

Data Index: 128665 (The Pile)

Max Activating Token Index: 1011

Text #3

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.8475. Min Act: -0.0000

Data Index: 878706 (The Pile)

Max Activating Token Index: 559

Text #4

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.8421. Min Act: -0.0000

Data Index: 100422 (The Pile)

Max Activating Token Index: 776

Text #5

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1159054 (The Pile)

Max Activating Token Index: 842

Text #6

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7483. Min Act: -0.0000

Data Index: 976198 (The Pile)

Max Activating Token Index: 75

Text #7

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7232. Min Act: -0.0000

Data Index: 215273 (The Pile)

Max Activating Token Index: 112

Text #8

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7104. Min Act: -0.0000

Data Index: 1576569 (The Pile)

Max Activating Token Index: 713

Text #9

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.7066. Min Act: -0.0000

Data Index: 1070177 (The Pile)

Max Activating Token Index: 365

Text #10

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6953. Min Act: -0.0000

Data Index: 126948 (The Pile)

Max Activating Token Index: 98

Text #11

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6941. Min Act: -0.0000

Data Index: 816974 (The Pile)

Max Activating Token Index: 271

Text #12

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1122781 (The Pile)

Max Activating Token Index: 551

Text #13

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6550. Min Act: -0.0000

Data Index: 401586 (The Pile)

Max Activating Token Index: 480

Text #14

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6540. Min Act: -0.0000

Data Index: 1221704 (The Pile)

Max Activating Token Index: 179

Text #15

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6942. Min Act: -0.0000

Data Index: 677456 (The Pile)

Max Activating Token Index: 98

Text #16

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1663281 (The Pile)

Max Activating Token Index: 506

Text #17

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1492639 (The Pile)

Max Activating Token Index: 918

Text #18

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1844210 (The Pile)

Max Activating Token Index: 822

Text #19

Max Range: 1.0525. Min Range: -1.0525

Max Act: 0.6584. Min Act: -0.0000

Data Index: 1214926 (The Pile)

Max Activating Token Index: 635