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

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

Neuron 5626 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.8392. Min Act: -0.0000

Data Index: 842568 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.7193. Min Act: -0.0000

Data Index: 817648 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.6799. Min Act: -0.0000

Data Index: 94555 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.6646. Min Act: -0.0000

Data Index: 795531 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.5925. Min Act: -0.0000

Data Index: 575649 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.5629. Min Act: -0.0000

Data Index: 840161 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.6483. Min Act: -0.0000

Data Index: 471146 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.5300. Min Act: -0.0000

Data Index: 188613 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.4965. Min Act: -0.0000

Data Index: 493557 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.3407. Min Act: -0.0000

Data Index: 951104 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.2527. Min Act: -0.0000

Data Index: 775840 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.3363. Min Act: -0.0000

Data Index: 727464 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.1927. Min Act: -0.0000

Data Index: 434720 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.2004. Min Act: -0.0000

Data Index: 965763 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.2775. Min Act: -0.0000

Data Index: 592943 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.2039. Min Act: -0.0000

Data Index: 1120605 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.1136. Min Act: -0.0000

Data Index: 1049511 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.2527. Min Act: -0.0000

Data Index: 809918 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.1642. Min Act: -0.0000

Data Index: 356447 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.1030. Min Act: -0.0000

Data Index: 40678 (C4 (Web Text))

Max Activating Token Index: 133