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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3348 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2089. Min Range: -4.2089

Max Act: 4.0266. Min Act: -0.0000

Data Index: 1146841 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 4.2089. Min Range: -4.2089

Max Act: 4.0047. Min Act: -0.0000

Data Index: 207598 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 4.2089. Min Range: -4.2089

Max Act: 3.9020. Min Act: -0.0000

Data Index: 1031318 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 4.2089. Min Range: -4.2089

Max Act: 3.8904. Min Act: -0.0000

Data Index: 937993 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 4.2089. Min Range: -4.2089

Max Act: 4.2089. Min Act: -0.0000

Data Index: 1159194 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 4.2089. Min Range: -4.2089

Max Act: 3.7041. Min Act: -0.0000

Data Index: 1304250 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 4.2089. Min Range: -4.2089

Max Act: 3.6847. Min Act: -0.0000

Data Index: 748370 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 4.2089. Min Range: -4.2089

Max Act: 3.9893. Min Act: -0.0000

Data Index: 263379 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 4.2089. Min Range: -4.2089

Max Act: 3.6063. Min Act: -0.0000

Data Index: 1144188 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 4.2089. Min Range: -4.2089

Max Act: 3.9282. Min Act: -0.0000

Data Index: 609253 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 4.2089. Min Range: -4.2089

Max Act: 3.6061. Min Act: -0.0000

Data Index: 358468 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 4.2089. Min Range: -4.2089

Max Act: 3.8797. Min Act: -0.0000

Data Index: 1326873 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 4.2089. Min Range: -4.2089

Max Act: 3.7110. Min Act: -0.0000

Data Index: 165416 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 4.2089. Min Range: -4.2089

Max Act: 3.3322. Min Act: -0.0000

Data Index: 518556 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 4.2089. Min Range: -4.2089

Max Act: 3.6616. Min Act: -0.0000

Data Index: 1195058 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 4.2089. Min Range: -4.2089

Max Act: 3.3036. Min Act: -0.0000

Data Index: 1139318 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 4.2089. Min Range: -4.2089

Max Act: 3.4358. Min Act: -0.0000

Data Index: 205465 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 4.2089. Min Range: -4.2089

Max Act: 3.5426. Min Act: -0.0000

Data Index: 31149 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 4.2089. Min Range: -4.2089

Max Act: 3.5064. Min Act: -0.0000

Data Index: 1148852 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 4.2089. Min Range: -4.2089

Max Act: 3.3530. Min Act: -0.0000

Data Index: 273906 (C4 (Web Text))

Max Activating Token Index: 56