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

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

Neuron 4837 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3533. Min Range: -2.3533

Max Act: 2.2405. Min Act: -0.0000

Data Index: 325642 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 2.3533. Min Range: -2.3533

Max Act: 2.3533. Min Act: -0.0000

Data Index: 138814 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 2.3533. Min Range: -2.3533

Max Act: 1.9799. Min Act: -0.0000

Data Index: 699733 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 2.3533. Min Range: -2.3533

Max Act: 1.9521. Min Act: -0.0000

Data Index: 279203 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 2.3533. Min Range: -2.3533

Max Act: 1.9219. Min Act: -0.0000

Data Index: 666127 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 2.3533. Min Range: -2.3533

Max Act: 1.8051. Min Act: -0.0000

Data Index: 669908 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 2.3533. Min Range: -2.3533

Max Act: 1.9108. Min Act: -0.0000

Data Index: 725527 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 2.3533. Min Range: -2.3533

Max Act: 1.8069. Min Act: -0.0000

Data Index: 170426 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 2.3533. Min Range: -2.3533

Max Act: 1.9050. Min Act: -0.0000

Data Index: 773816 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 2.3533. Min Range: -2.3533

Max Act: 1.7911. Min Act: -0.0000

Data Index: 494493 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 2.3533. Min Range: -2.3533

Max Act: 1.6457. Min Act: -0.0000

Data Index: 782060 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 2.3533. Min Range: -2.3533

Max Act: 1.7964. Min Act: -0.0000

Data Index: 556521 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 2.3533. Min Range: -2.3533

Max Act: 1.8957. Min Act: -0.0000

Data Index: 847445 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 2.3533. Min Range: -2.3533

Max Act: 1.8076. Min Act: -0.0000

Data Index: 1101797 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 2.3533. Min Range: -2.3533

Max Act: 1.8434. Min Act: -0.0000

Data Index: 1155232 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 2.3533. Min Range: -2.3533

Max Act: 1.6272. Min Act: -0.0000

Data Index: 520438 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 2.3533. Min Range: -2.3533

Max Act: 1.6302. Min Act: -0.0000

Data Index: 820528 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 2.3533. Min Range: -2.3533

Max Act: 1.7073. Min Act: -0.0000

Data Index: 1165716 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 2.3533. Min Range: -2.3533

Max Act: 1.5759. Min Act: -0.0000

Data Index: 201655 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 2.3533. Min Range: -2.3533

Max Act: 1.6926. Min Act: -0.0000

Data Index: 343598 (C4 (Web Text))

Max Activating Token Index: 323