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

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

Neuron 4169 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: 3.6550. Min Range: -3.6550

Max Act: 3.6550. Min Act: -0.0000

Data Index: 245214 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 3.6550. Min Range: -3.6550

Max Act: 3.5779. Min Act: -0.0000

Data Index: 428793 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 3.6550. Min Range: -3.6550

Max Act: 3.2062. Min Act: -0.0000

Data Index: 564069 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 3.6550. Min Range: -3.6550

Max Act: 3.1971. Min Act: -0.0000

Data Index: 1024466 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 3.6550. Min Range: -3.6550

Max Act: 3.1893. Min Act: -0.0000

Data Index: 670936 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 3.6550. Min Range: -3.6550

Max Act: 3.1743. Min Act: -0.0000

Data Index: 1221036 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 3.6550. Min Range: -3.6550

Max Act: 3.0312. Min Act: -0.0000

Data Index: 1079531 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 3.6550. Min Range: -3.6550

Max Act: 2.9714. Min Act: -0.0000

Data Index: 1099308 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 3.6550. Min Range: -3.6550

Max Act: 3.1244. Min Act: -0.0000

Data Index: 1125527 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 3.6550. Min Range: -3.6550

Max Act: 3.1312. Min Act: -0.0000

Data Index: 729447 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 3.6550. Min Range: -3.6550

Max Act: 3.2388. Min Act: -0.0000

Data Index: 593506 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 3.6550. Min Range: -3.6550

Max Act: 2.8042. Min Act: -0.0000

Data Index: 322013 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 3.6550. Min Range: -3.6550

Max Act: 3.0544. Min Act: -0.0000

Data Index: 264650 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 3.6550. Min Range: -3.6550

Max Act: 3.0310. Min Act: -0.0000

Data Index: 83742 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 3.6550. Min Range: -3.6550

Max Act: 3.0382. Min Act: -0.0000

Data Index: 897498 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 3.6550. Min Range: -3.6550

Max Act: 3.1026. Min Act: -0.0001

Data Index: 653890 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 3.6550. Min Range: -3.6550

Max Act: 2.9691. Min Act: -0.0001

Data Index: 947611 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 3.6550. Min Range: -3.6550

Max Act: 2.9840. Min Act: -0.0000

Data Index: 1013175 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 3.6550. Min Range: -3.6550

Max Act: 2.9631. Min Act: -0.0000

Data Index: 6719 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 3.6550. Min Range: -3.6550

Max Act: 2.8063. Min Act: -0.0001

Data Index: 858659 (C4 (Web Text))

Max Activating Token Index: 845