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

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

Neuron 4019 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.5258. Min Act: -0.0000

Data Index: 780032 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.4066. Min Act: -0.0000

Data Index: 1212625 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.3782. Min Act: -0.0000

Data Index: 1097726 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.3027. Min Act: -0.0000

Data Index: 1217102 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.3517. Min Act: -0.0000

Data Index: 336595 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.2850. Min Act: -0.0000

Data Index: 911369 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.2562. Min Act: -0.0000

Data Index: 652330 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.1343. Min Act: -0.0000

Data Index: 80231 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.0740. Min Act: -0.0000

Data Index: 114741 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.1205. Min Act: -0.0000

Data Index: 159075 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.0932. Min Act: -0.0000

Data Index: 335461 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.1639. Min Act: -0.0000

Data Index: 45149 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.0236. Min Act: -0.0000

Data Index: 998945 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.0829. Min Act: -0.0000

Data Index: 1229807 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.1420. Min Act: -0.0000

Data Index: 480426 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.1245. Min Act: -0.0000

Data Index: 220882 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.0567. Min Act: -0.0000

Data Index: 226445 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.0312. Min Act: -0.0000

Data Index: 1067438 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 1.5258. Min Range: -1.5258

Max Act: 1.0305. Min Act: -0.0000

Data Index: 490233 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 1.5258. Min Range: -1.5258

Max Act: 0.9678. Min Act: -0.0000

Data Index: 558453 (C4 (Web Text))

Max Activating Token Index: 87