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

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

Neuron 3139 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: 0.0499. Min Range: -0.0499

Max Act: 0.0499. Min Act: -0.0001

Data Index: 648012 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0452. Min Act: -0.0001

Data Index: 72995 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0458. Min Act: -0.0002

Data Index: 273152 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0458. Min Act: -0.0001

Data Index: 503888 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0455. Min Act: -0.0001

Data Index: 1027302 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1222174 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0456. Min Act: -0.0002

Data Index: 789675 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0439. Min Act: -0.0002

Data Index: 572843 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0445. Min Act: -0.0001

Data Index: 441772 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0485. Min Act: -0.0001

Data Index: 682875 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0407. Min Act: -0.0002

Data Index: 363804 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0431. Min Act: -0.0001

Data Index: 586482 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0366. Min Act: -0.0001

Data Index: 246990 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0427. Min Act: -0.0001

Data Index: 137827 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0422. Min Act: -0.0002

Data Index: 497201 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0420. Min Act: -0.0001

Data Index: 444246 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0406. Min Act: -0.0001

Data Index: 505237 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0437. Min Act: -0.0001

Data Index: 1228542 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1059204 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0375. Min Act: -0.0002

Data Index: 642037 (C4 (Web Text))

Max Activating Token Index: 934