Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4861 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.8441. Min Act: -0.0001

Data Index: 986304 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7481. Min Act: -0.0001

Data Index: 285197 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7951. Min Act: -0.0001

Data Index: 578610 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7635. Min Act: -0.0001

Data Index: 778274 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6939. Min Act: -0.0001

Data Index: 333193 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6596. Min Act: -0.0001

Data Index: 518968 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7145. Min Act: -0.0001

Data Index: 554254 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6889. Min Act: -0.0001

Data Index: 1192953 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6643. Min Act: -0.0001

Data Index: 477209 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6506. Min Act: -0.0001

Data Index: 813043 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6728. Min Act: -0.0001

Data Index: 1190940 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.5882. Min Act: -0.0001

Data Index: 1030955 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6666. Min Act: -0.0001

Data Index: 718367 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6401. Min Act: -0.0001

Data Index: 1208027 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6565. Min Act: -0.0001

Data Index: 999168 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6306. Min Act: -0.0001

Data Index: 754487 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.5868. Min Act: -0.0001

Data Index: 210470 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.5786. Min Act: -0.0001

Data Index: 23958 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.5643. Min Act: -0.0001

Data Index: 1286777 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6182. Min Act: -0.0001

Data Index: 554416 (C4 (Web Text))

Max Activating Token Index: 781