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

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

Neuron 1255 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: 1.1969. Min Range: -1.1969

Max Act: 1.1969. Min Act: -0.0001

Data Index: 425909 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.8929. Min Act: -0.0001

Data Index: 583031 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.8484. Min Act: -0.0001

Data Index: 1352205 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.8966. Min Act: -0.0001

Data Index: 290585 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.8185. Min Act: -0.0001

Data Index: 980497 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.8137. Min Act: -0.0001

Data Index: 784493 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7598. Min Act: -0.0001

Data Index: 778383 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7676. Min Act: -0.0001

Data Index: 944141 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7727. Min Act: -0.0001

Data Index: 265286 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7640. Min Act: -0.0001

Data Index: 811608 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.8090. Min Act: -0.0001

Data Index: 1006554 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7568. Min Act: -0.0001

Data Index: 165794 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7937. Min Act: -0.0001

Data Index: 626534 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.6892. Min Act: -0.0001

Data Index: 135157 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7664. Min Act: -0.0001

Data Index: 75813 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7581. Min Act: -0.0001

Data Index: 1280948 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7479. Min Act: -0.0001

Data Index: 353246 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7563. Min Act: -0.0001

Data Index: 705323 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7684. Min Act: -0.0001

Data Index: 500409 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 1.1969. Min Range: -1.1969

Max Act: 0.7429. Min Act: -0.0001

Data Index: 747157 (C4 (Web Text))

Max Activating Token Index: 533