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

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

Neuron 3283 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.6741. Min Act: -0.0001

Data Index: 568243 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.5024. Min Act: -0.0001

Data Index: 32314 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.4389. Min Act: -0.0001

Data Index: 789302 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.4386. Min Act: -0.0001

Data Index: 1221107 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.3872. Min Act: -0.0002

Data Index: 294572 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.2989. Min Act: -0.0001

Data Index: 570500 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.3558. Min Act: -0.0002

Data Index: 31646 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.3454. Min Act: -0.0002

Data Index: 383843 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.4339. Min Act: -0.0001

Data Index: 209892 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.3970. Min Act: -0.0001

Data Index: 329572 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.2769. Min Act: -0.0001

Data Index: 1171843 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.3807. Min Act: -0.0002

Data Index: 227985 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.1522. Min Act: -0.0001

Data Index: 1260633 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.3808. Min Act: -0.0001

Data Index: 1334603 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.3276. Min Act: -0.0002

Data Index: 379379 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.3193. Min Act: -0.0001

Data Index: 1260570 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.1805. Min Act: -0.0001

Data Index: 1110783 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.2388. Min Act: -0.0001

Data Index: 672240 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.3416. Min Act: -0.0001

Data Index: 178772 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 1.6741. Min Range: -1.6741

Max Act: 1.2308. Min Act: -0.0002

Data Index: 871513 (C4 (Web Text))

Max Activating Token Index: 321