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

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

Neuron 2796 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2520. Min Range: -1.2520

Max Act: 1.2520. Min Act: -0.0001

Data Index: 252079 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 1.2520. Min Range: -1.2520

Max Act: 1.1819. Min Act: -0.0001

Data Index: 6819 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 1.2520. Min Range: -1.2520

Max Act: 1.1683. Min Act: -0.0001

Data Index: 119678 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 1.2520. Min Range: -1.2520

Max Act: 1.1894. Min Act: -0.0001

Data Index: 663317 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 1.2520. Min Range: -1.2520

Max Act: 1.0228. Min Act: -0.0001

Data Index: 745536 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 1.2520. Min Range: -1.2520

Max Act: 1.0456. Min Act: -0.0001

Data Index: 345755 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 1.2520. Min Range: -1.2520

Max Act: 1.0243. Min Act: -0.0001

Data Index: 417721 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 1.2520. Min Range: -1.2520

Max Act: 0.9428. Min Act: -0.0001

Data Index: 272122 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 1.2520. Min Range: -1.2520

Max Act: 0.9518. Min Act: -0.0001

Data Index: 861578 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 1.2520. Min Range: -1.2520

Max Act: 1.0122. Min Act: -0.0001

Data Index: 756640 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 1.2520. Min Range: -1.2520

Max Act: 1.0063. Min Act: -0.0001

Data Index: 46046 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 1.2520. Min Range: -1.2520

Max Act: 1.0072. Min Act: -0.0001

Data Index: 453510 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 1.2520. Min Range: -1.2520

Max Act: 1.0598. Min Act: -0.0001

Data Index: 1247352 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 1.2520. Min Range: -1.2520

Max Act: 0.9634. Min Act: -0.0001

Data Index: 614270 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 1.2520. Min Range: -1.2520

Max Act: 0.9736. Min Act: -0.0001

Data Index: 463350 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 1.2520. Min Range: -1.2520

Max Act: 0.9406. Min Act: -0.0001

Data Index: 814973 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 1.2520. Min Range: -1.2520

Max Act: 0.9434. Min Act: -0.0001

Data Index: 1053895 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 1.2520. Min Range: -1.2520

Max Act: 0.9473. Min Act: -0.0001

Data Index: 617963 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 1.2520. Min Range: -1.2520

Max Act: 0.8755. Min Act: -0.0001

Data Index: 434465 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 1.2520. Min Range: -1.2520

Max Act: 0.9033. Min Act: -0.0001

Data Index: 975969 (C4 (Web Text))

Max Activating Token Index: 54