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

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

Neuron 880 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1381. Min Range: -1.1381

Max Act: 1.1381. Min Act: -0.0000

Data Index: 93367 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 1.1381. Min Range: -1.1381

Max Act: 1.1165. Min Act: -0.0000

Data Index: 1159565 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 1.1381. Min Range: -1.1381

Max Act: 1.0737. Min Act: -0.0000

Data Index: 47063 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 1.1381. Min Range: -1.1381

Max Act: 1.0151. Min Act: -0.0000

Data Index: 464302 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 1.1381. Min Range: -1.1381

Max Act: 1.1082. Min Act: -0.0000

Data Index: 1281429 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 1.1381. Min Range: -1.1381

Max Act: 1.0531. Min Act: -0.0000

Data Index: 701294 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.9684. Min Act: -0.0001

Data Index: 447159 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.9873. Min Act: -0.0000

Data Index: 1356483 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.9954. Min Act: -0.0000

Data Index: 890145 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.9556. Min Act: -0.0000

Data Index: 847651 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.9405. Min Act: -0.0000

Data Index: 795057 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.9534. Min Act: -0.0000

Data Index: 117166 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1280640 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.8841. Min Act: -0.0000

Data Index: 106696 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.9070. Min Act: -0.0000

Data Index: 561163 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.9330. Min Act: -0.0000

Data Index: 1014978 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.8770. Min Act: -0.0001

Data Index: 855316 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.9328. Min Act: -0.0000

Data Index: 1081932 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.8925. Min Act: -0.0000

Data Index: 941756 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 1.1381. Min Range: -1.1381

Max Act: 0.8887. Min Act: -0.0000

Data Index: 1042130 (C4 (Web Text))

Max Activating Token Index: 891