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

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

Neuron 368 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0862. Min Act: -0.0000

Data Index: 431535 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0740. Min Act: -0.0000

Data Index: 1285666 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0783. Min Act: -0.0000

Data Index: 735306 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0613. Min Act: -0.0000

Data Index: 1291596 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0736. Min Act: -0.0000

Data Index: 1353228 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0690. Min Act: -0.0000

Data Index: 1243756 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0656. Min Act: -0.0000

Data Index: 1369316 (Python Code)

Max Activating Token Index: 362

Text #7

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0689. Min Act: -0.0000

Data Index: 382844 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0584. Min Act: -0.0000

Data Index: 1086844 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0646. Min Act: -0.0000

Data Index: 1260016 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0581. Min Act: -0.0000

Data Index: 1000707 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1255347 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0592. Min Act: -0.0000

Data Index: 1024412 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0618. Min Act: -0.0001

Data Index: 8229 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0609. Min Act: -0.0000

Data Index: 247299 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0583. Min Act: -0.0001

Data Index: 147321 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0574. Min Act: -0.0000

Data Index: 1466033 (Python Code)

Max Activating Token Index: 286

Text #17

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0559. Min Act: -0.0000

Data Index: 340754 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0643. Min Act: -0.0000

Data Index: 1105474 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0577. Min Act: -0.0000

Data Index: 305960 (C4 (Web Text))

Max Activating Token Index: 669