Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3489 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1352664 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.7535. Min Act: -0.0000

Data Index: 406685 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6537. Min Act: -0.0000

Data Index: 367026 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6439. Min Act: 0.0000

Data Index: 638174 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6251. Min Act: -0.0000

Data Index: 843699 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6240. Min Act: -0.0000

Data Index: 1122051 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6030. Min Act: 0.0000

Data Index: 503384 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1086862 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5962. Min Act: -0.0000

Data Index: 154191 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1359406 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6254. Min Act: 0.0000

Data Index: 372846 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1273319 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6096. Min Act: -0.0000

Data Index: 133406 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6041. Min Act: -0.0000

Data Index: 494279 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1128813 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5660. Min Act: -0.0000

Data Index: 947827 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5701. Min Act: -0.0000

Data Index: 707450 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5635. Min Act: 0.0000

Data Index: 294194 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5551. Min Act: -0.0000

Data Index: 955355 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5510. Min Act: -0.0000

Data Index: 211612 (C4 (Web Text))

Max Activating Token Index: 76