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

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

Neuron 401 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: 3.6572. Min Range: -3.6572

Max Act: 3.2690. Min Act: -0.0001

Data Index: 794637 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 3.6572. Min Range: -3.6572

Max Act: 3.5437. Min Act: -0.0001

Data Index: 947375 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 3.6572. Min Range: -3.6572

Max Act: 3.6572. Min Act: -0.0001

Data Index: 706997 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 3.6572. Min Range: -3.6572

Max Act: 3.4843. Min Act: -0.0001

Data Index: 696438 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 3.6572. Min Range: -3.6572

Max Act: 3.1842. Min Act: -0.0001

Data Index: 563588 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 3.6572. Min Range: -3.6572

Max Act: 3.1508. Min Act: -0.0001

Data Index: 246126 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 3.6572. Min Range: -3.6572

Max Act: 3.2549. Min Act: -0.0001

Data Index: 1252082 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 3.6572. Min Range: -3.6572

Max Act: 3.0630. Min Act: -0.0001

Data Index: 396757 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 3.6572. Min Range: -3.6572

Max Act: 3.0730. Min Act: -0.0001

Data Index: 650290 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 3.6572. Min Range: -3.6572

Max Act: 3.3527. Min Act: -0.0001

Data Index: 1285762 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 3.6572. Min Range: -3.6572

Max Act: 2.9877. Min Act: -0.0001

Data Index: 90071 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 3.6572. Min Range: -3.6572

Max Act: 2.4517. Min Act: -0.0001

Data Index: 981993 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 3.6572. Min Range: -3.6572

Max Act: 2.9807. Min Act: -0.0001

Data Index: 1348279 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 3.6572. Min Range: -3.6572

Max Act: 2.7037. Min Act: -0.0001

Data Index: 356922 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 3.6572. Min Range: -3.6572

Max Act: 2.7993. Min Act: -0.0001

Data Index: 550173 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 3.6572. Min Range: -3.6572

Max Act: 2.7833. Min Act: -0.0001

Data Index: 1188575 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 3.6572. Min Range: -3.6572

Max Act: 2.7708. Min Act: -0.0001

Data Index: 368644 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 3.6572. Min Range: -3.6572

Max Act: 2.8629. Min Act: -0.0001

Data Index: 1204169 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 3.6572. Min Range: -3.6572

Max Act: 2.6755. Min Act: -0.0001

Data Index: 607294 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 3.6572. Min Range: -3.6572

Max Act: 2.7832. Min Act: -0.0001

Data Index: 621296 (C4 (Web Text))

Max Activating Token Index: 133