Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 555 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0970. Min Act: -0.0002

Data Index: 146900 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0879. Min Act: -0.0002

Data Index: 1019611 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1199679 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0876. Min Act: -0.0002

Data Index: 31702 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0748. Min Act: -0.0002

Data Index: 13259 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0789. Min Act: -0.0002

Data Index: 996845 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0780. Min Act: -0.0002

Data Index: 898870 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0814. Min Act: -0.0002

Data Index: 719103 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0758. Min Act: -0.0002

Data Index: 913648 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0814. Min Act: -0.0002

Data Index: 480433 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0687. Min Act: -0.0002

Data Index: 523404 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0657. Min Act: -0.0002

Data Index: 402557 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0625. Min Act: -0.0002

Data Index: 365880 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0621. Min Act: -0.0002

Data Index: 966238 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0616. Min Act: -0.0002

Data Index: 1027733 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0520. Min Act: -0.0002

Data Index: 325615 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1281269 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0583. Min Act: -0.0002

Data Index: 628281 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0583. Min Act: -0.0002

Data Index: 941051 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1144192 (C4 (Web Text))

Max Activating Token Index: 155