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

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

Neuron 1279 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: 3.9424. Min Range: -3.9424

Max Act: 3.8049. Min Act: -0.0001

Data Index: 608415 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 3.9424. Min Range: -3.9424

Max Act: 3.9424. Min Act: -0.0001

Data Index: 1081313 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 3.9424. Min Range: -3.9424

Max Act: 3.5740. Min Act: -0.0001

Data Index: 871461 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 3.9424. Min Range: -3.9424

Max Act: 3.7334. Min Act: -0.0001

Data Index: 343110 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 3.9424. Min Range: -3.9424

Max Act: 3.3595. Min Act: -0.0001

Data Index: 61741 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 3.9424. Min Range: -3.9424

Max Act: 3.2805. Min Act: -0.0001

Data Index: 99796 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 3.9424. Min Range: -3.9424

Max Act: 3.2272. Min Act: -0.0001

Data Index: 246951 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 3.9424. Min Range: -3.9424

Max Act: 3.1744. Min Act: -0.0001

Data Index: 428334 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 3.9424. Min Range: -3.9424

Max Act: 3.1688. Min Act: -0.0001

Data Index: 126520 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 3.9424. Min Range: -3.9424

Max Act: 3.3098. Min Act: -0.0001

Data Index: 391395 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 3.9424. Min Range: -3.9424

Max Act: 2.8474. Min Act: -0.0001

Data Index: 141755 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 3.9424. Min Range: -3.9424

Max Act: 2.3867. Min Act: -0.0001

Data Index: 5646 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 3.9424. Min Range: -3.9424

Max Act: 2.4893. Min Act: -0.0001

Data Index: 833192 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 3.9424. Min Range: -3.9424

Max Act: 2.4473. Min Act: -0.0001

Data Index: 1282039 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 3.9424. Min Range: -3.9424

Max Act: 2.4103. Min Act: -0.0001

Data Index: 861101 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 3.9424. Min Range: -3.9424

Max Act: 2.1804. Min Act: -0.0001

Data Index: 1113975 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 3.9424. Min Range: -3.9424

Max Act: 2.1210. Min Act: -0.0001

Data Index: 376777 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 3.9424. Min Range: -3.9424

Max Act: 2.2012. Min Act: -0.0001

Data Index: 539584 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 3.9424. Min Range: -3.9424

Max Act: 1.9926. Min Act: -0.0001

Data Index: 279358 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 3.9424. Min Range: -3.9424

Max Act: 2.0697. Min Act: -0.0001

Data Index: 776633 (C4 (Web Text))

Max Activating Token Index: 579