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

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

Neuron 4676 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.9484. Min Act: -0.0002

Data Index: 570738 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.5100. Min Act: -0.0002

Data Index: 290928 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.5000. Min Act: -0.0002

Data Index: 572182 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.5113. Min Act: -0.0002

Data Index: 719688 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.5247. Min Act: -0.0002

Data Index: 89031 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.5034. Min Act: -0.0002

Data Index: 155720 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.5158. Min Act: -0.0002

Data Index: 597266 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.4849. Min Act: -0.0002

Data Index: 1325622 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.4810. Min Act: -0.0002

Data Index: 379927 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.4576. Min Act: -0.0002

Data Index: 496199 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.4505. Min Act: -0.0002

Data Index: 1016556 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.4462. Min Act: -0.0002

Data Index: 287376 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.4705. Min Act: -0.0002

Data Index: 851940 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.4271. Min Act: -0.0002

Data Index: 1355514 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.4499. Min Act: -0.0002

Data Index: 866759 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.4467. Min Act: -0.0002

Data Index: 1012932 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.4462. Min Act: -0.0002

Data Index: 1086491 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.4137. Min Act: -0.0002

Data Index: 355127 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.4007. Min Act: -0.0002

Data Index: 1070402 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.9484. Min Range: -0.9484

Max Act: 0.4216. Min Act: -0.0003

Data Index: 183354 (C4 (Web Text))

Max Activating Token Index: 712