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

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

Neuron 384 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.8518. Min Act: -0.0001

Data Index: 336534 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.8469. Min Act: -0.0001

Data Index: 247276 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.8091. Min Act: -0.0001

Data Index: 963784 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.8612. Min Act: -0.0001

Data Index: 830987 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.7607. Min Act: -0.0001

Data Index: 1147703 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.6217. Min Act: -0.0001

Data Index: 457770 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.7131. Min Act: -0.0001

Data Index: 169490 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.6150. Min Act: -0.0001

Data Index: 1159055 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.6917. Min Act: -0.0001

Data Index: 1058257 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.6006. Min Act: -0.0001

Data Index: 211920 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.5749. Min Act: -0.0001

Data Index: 1024411 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.6666. Min Act: -0.0001

Data Index: 837343 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.6650. Min Act: -0.0001

Data Index: 694619 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.5446. Min Act: -0.0001

Data Index: 352834 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.6036. Min Act: -0.0001

Data Index: 245803 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.5170. Min Act: -0.0001

Data Index: 603308 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.6876. Min Act: -0.0001

Data Index: 573673 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.5081. Min Act: -0.0001

Data Index: 1306777 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.5313. Min Act: -0.0001

Data Index: 509322 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 1.8612. Min Range: -1.8612

Max Act: 1.4958. Min Act: -0.0001

Data Index: 962239 (C4 (Web Text))

Max Activating Token Index: 630