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

Dataset: The Pile

Neuron 783 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5228. Min Range: -5.5228

Max Act: 5.5228. Min Act: -0.0000

Data Index: 456750 (The Pile)

Max Activating Token Index: 94

Text #1

Max Range: 5.5228. Min Range: -5.5228

Max Act: 3.9439. Min Act: -0.0000

Data Index: 1295567 (The Pile)

Max Activating Token Index: 947

Text #2

Max Range: 5.5228. Min Range: -5.5228

Max Act: 3.7981. Min Act: -0.0000

Data Index: 77743 (The Pile)

Max Activating Token Index: 376

Text #3

Max Range: 5.5228. Min Range: -5.5228

Max Act: 3.8081. Min Act: -0.0000

Data Index: 1536361 (The Pile)

Max Activating Token Index: 860

Text #4

Max Range: 5.5228. Min Range: -5.5228

Max Act: 3.6954. Min Act: -0.0000

Data Index: 1358382 (The Pile)

Max Activating Token Index: 987

Text #5

Max Range: 5.5228. Min Range: -5.5228

Max Act: 3.7512. Min Act: -0.0000

Data Index: 781244 (The Pile)

Max Activating Token Index: 750

Text #6

Max Range: 5.5228. Min Range: -5.5228

Max Act: 3.4851. Min Act: -0.0000

Data Index: 1979818 (The Pile)

Max Activating Token Index: 412

Text #7

Max Range: 5.5228. Min Range: -5.5228

Max Act: 3.4476. Min Act: -0.0000

Data Index: 1043955 (The Pile)

Max Activating Token Index: 665

Text #8

Max Range: 5.5228. Min Range: -5.5228

Max Act: 3.4628. Min Act: -0.0000

Data Index: 163937 (The Pile)

Max Activating Token Index: 165

Text #9

Max Range: 5.5228. Min Range: -5.5228

Max Act: 3.4307. Min Act: -0.0000

Data Index: 696699 (The Pile)

Max Activating Token Index: 905

Text #10

Max Range: 5.5228. Min Range: -5.5228

Max Act: 3.2694. Min Act: -0.0000

Data Index: 174528 (The Pile)

Max Activating Token Index: 494

Text #11

Max Range: 5.5228. Min Range: -5.5228

Max Act: 3.3392. Min Act: -0.0000

Data Index: 1147789 (The Pile)

Max Activating Token Index: 659

Text #12

Max Range: 5.5228. Min Range: -5.5228

Max Act: 3.2120. Min Act: -0.0000

Data Index: 1157640 (The Pile)

Max Activating Token Index: 861

Text #13

Max Range: 5.5228. Min Range: -5.5228

Max Act: 3.2128. Min Act: -0.0000

Data Index: 1178265 (The Pile)

Max Activating Token Index: 221

Text #14

Max Range: 5.5228. Min Range: -5.5228

Max Act: 3.0053. Min Act: -0.0000

Data Index: 1042454 (The Pile)

Max Activating Token Index: 389

Text #15

Max Range: 5.5228. Min Range: -5.5228

Max Act: 3.3658. Min Act: -0.0000

Data Index: 1694103 (The Pile)

Max Activating Token Index: 851

Text #16

Max Range: 5.5228. Min Range: -5.5228

Max Act: 2.9495. Min Act: -0.0000

Data Index: 977009 (The Pile)

Max Activating Token Index: 651

Text #17

Max Range: 5.5228. Min Range: -5.5228

Max Act: 3.3062. Min Act: -0.0000

Data Index: 143238 (The Pile)

Max Activating Token Index: 295

Text #18

Max Range: 5.5228. Min Range: -5.5228

Max Act: 2.8285. Min Act: -0.0000

Data Index: 745014 (The Pile)

Max Activating Token Index: 462

Text #19

Max Range: 5.5228. Min Range: -5.5228

Max Act: 2.7433. Min Act: -0.0000

Data Index: 1164469 (The Pile)

Max Activating Token Index: 399