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

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

Neuron 4447 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: 1.6344. Min Range: -1.6344

Max Act: 1.6344. Min Act: -0.0001

Data Index: 1177811 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.6244. Min Act: -0.0001

Data Index: 49414 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.5844. Min Act: -0.0001

Data Index: 612700 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.5514. Min Act: -0.0001

Data Index: 347974 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.4473. Min Act: -0.0001

Data Index: 827316 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.5017. Min Act: -0.0000

Data Index: 145843 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.4731. Min Act: -0.0000

Data Index: 945106 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.4802. Min Act: -0.0001

Data Index: 238855 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.3788. Min Act: -0.0001

Data Index: 897465 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.4698. Min Act: -0.0001

Data Index: 1050126 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.4586. Min Act: -0.0001

Data Index: 1194971 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.4874. Min Act: -0.0001

Data Index: 1028650 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.3648. Min Act: -0.0001

Data Index: 34665 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.3227. Min Act: -0.0001

Data Index: 1196977 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.5226. Min Act: -0.0001

Data Index: 666136 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.4352. Min Act: -0.0001

Data Index: 323088 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.3875. Min Act: -0.0001

Data Index: 503150 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.4287. Min Act: -0.0000

Data Index: 209797 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.3848. Min Act: -0.0001

Data Index: 508929 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.4070. Min Act: -0.0001

Data Index: 423534 (C4 (Web Text))

Max Activating Token Index: 472