Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 178 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.5335. Min Act: -0.0003

Data Index: 567789 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4932. Min Act: -0.0003

Data Index: 1106778 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4963. Min Act: -0.0003

Data Index: 421691 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4633. Min Act: -0.0003

Data Index: 1094488 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4763. Min Act: -0.0003

Data Index: 364705 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4933. Min Act: -0.0003

Data Index: 755650 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4697. Min Act: -0.0003

Data Index: 1315666 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4672. Min Act: -0.0003

Data Index: 953755 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4829. Min Act: -0.0003

Data Index: 556211 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4782. Min Act: -0.0003

Data Index: 998141 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4731. Min Act: -0.0003

Data Index: 802834 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4393. Min Act: -0.0003

Data Index: 1307869 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4671. Min Act: -0.0003

Data Index: 1143968 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4459. Min Act: -0.0003

Data Index: 761099 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4457. Min Act: -0.0003

Data Index: 693533 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4421. Min Act: -0.0003

Data Index: 204704 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4561. Min Act: -0.0003

Data Index: 727563 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4408. Min Act: -0.0003

Data Index: 609772 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4373. Min Act: -0.0003

Data Index: 662901 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.5335. Min Range: -0.5335

Max Act: 0.4556. Min Act: -0.0003

Data Index: 219115 (C4 (Web Text))

Max Activating Token Index: 173