Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 87 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.7654. Min Act: -0.0001

Data Index: 846368 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.6918. Min Act: -0.0001

Data Index: 616646 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5763. Min Act: -0.0001

Data Index: 1342354 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5615. Min Act: -0.0001

Data Index: 938951 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5527. Min Act: -0.0001

Data Index: 438640 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5472. Min Act: -0.0001

Data Index: 861664 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5402. Min Act: -0.0001

Data Index: 11036 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5967. Min Act: -0.0001

Data Index: 1137650 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5343. Min Act: -0.0001

Data Index: 726685 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5229. Min Act: -0.0001

Data Index: 1003619 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5218. Min Act: -0.0001

Data Index: 182800 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5420. Min Act: -0.0001

Data Index: 111332 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5291. Min Act: -0.0001

Data Index: 855612 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5009. Min Act: -0.0001

Data Index: 1046672 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5371. Min Act: -0.0001

Data Index: 120787 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5825. Min Act: -0.0001

Data Index: 785610 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5232. Min Act: -0.0001

Data Index: 1142592 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.4566. Min Act: -0.0001

Data Index: 1150175 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.4859. Min Act: -0.0001

Data Index: 197223 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.7654. Min Range: -0.7654

Max Act: 0.5000. Min Act: -0.0001

Data Index: 1096133 (C4 (Web Text))

Max Activating Token Index: 257