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

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

Neuron 3516 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1350. Min Act: -0.0001

Data Index: 308447 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1260. Min Act: -0.0001

Data Index: 526930 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1104. Min Act: -0.0001

Data Index: 578954 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1238. Min Act: -0.0001

Data Index: 29723 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1000. Min Act: -0.0001

Data Index: 106119 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1032. Min Act: -0.0001

Data Index: 296650 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1028. Min Act: -0.0001

Data Index: 766907 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1048. Min Act: -0.0001

Data Index: 399235 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1174074 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1045. Min Act: -0.0001

Data Index: 35772 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0964. Min Act: -0.0001

Data Index: 967158 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0996. Min Act: -0.0001

Data Index: 397552 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0974. Min Act: -0.0001

Data Index: 787206 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0967. Min Act: -0.0001

Data Index: 79672 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0957. Min Act: -0.0001

Data Index: 751999 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0888. Min Act: -0.0001

Data Index: 1141482 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0921. Min Act: -0.0001

Data Index: 883252 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0879. Min Act: -0.0001

Data Index: 349412 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0873. Min Act: -0.0001

Data Index: 881404 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0907. Min Act: -0.0001

Data Index: 481621 (C4 (Web Text))

Max Activating Token Index: 976