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

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

Neuron 5245 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: 1.9703. Min Range: -1.9703

Max Act: 1.9703. Min Act: -0.0000

Data Index: 1348260 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.2521. Min Act: -0.0000

Data Index: 1110507 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.2046. Min Act: -0.0000

Data Index: 1201735 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.1094. Min Act: -0.0000

Data Index: 285801 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.1191. Min Act: -0.0000

Data Index: 601066 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.1192. Min Act: -0.0001

Data Index: 105838 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.1002. Min Act: -0.0000

Data Index: 1474961 (Python Code)

Max Activating Token Index: 340

Text #7

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.0919. Min Act: -0.0000

Data Index: 1412929 (Python Code)

Max Activating Token Index: 666

Text #8

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.0162. Min Act: -0.0001

Data Index: 991069 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.0145. Min Act: -0.0000

Data Index: 1393823 (Python Code)

Max Activating Token Index: 696

Text #10

Max Range: 1.9703. Min Range: -1.9703

Max Act: 0.9990. Min Act: -0.0000

Data Index: 250682 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 1.9703. Min Range: -1.9703

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1541457 (Python Code)

Max Activating Token Index: 575

Text #12

Max Range: 1.9703. Min Range: -1.9703

Max Act: 1.0052. Min Act: -0.0000

Data Index: 1034861 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 1.9703. Min Range: -1.9703

Max Act: 0.9657. Min Act: -0.0000

Data Index: 247244 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 1.9703. Min Range: -1.9703

Max Act: 0.9688. Min Act: -0.0001

Data Index: 773057 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 1.9703. Min Range: -1.9703

Max Act: 0.9080. Min Act: -0.0000

Data Index: 1535035 (Python Code)

Max Activating Token Index: 111

Text #16

Max Range: 1.9703. Min Range: -1.9703

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1190640 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 1.9703. Min Range: -1.9703

Max Act: 0.9277. Min Act: -0.0000

Data Index: 1418541 (Python Code)

Max Activating Token Index: 120

Text #18

Max Range: 1.9703. Min Range: -1.9703

Max Act: 0.9422. Min Act: -0.0000

Data Index: 1450575 (Python Code)

Max Activating Token Index: 925

Text #19

Max Range: 1.9703. Min Range: -1.9703

Max Act: 0.8896. Min Act: -0.0000

Data Index: 1502768 (Python Code)

Max Activating Token Index: 620