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

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

Neuron 1745 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.3497. Min Act: -0.0001

Data Index: 1064400 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.3544. Min Act: -0.0001

Data Index: 72904 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.1099. Min Act: -0.0001

Data Index: 1283206 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.0958. Min Act: -0.0001

Data Index: 102980 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.0466. Min Act: -0.0001

Data Index: 1077590 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.0313. Min Act: -0.0001

Data Index: 324508 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 1.3544. Min Range: -1.3544

Max Act: 1.0210. Min Act: -0.0001

Data Index: 633684 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.9325. Min Act: -0.0001

Data Index: 247094 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.9775. Min Act: -0.0001

Data Index: 320358 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.9754. Min Act: -0.0001

Data Index: 478829 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.9521. Min Act: -0.0001

Data Index: 784278 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.9240. Min Act: -0.0001

Data Index: 626539 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.8525. Min Act: -0.0001

Data Index: 1318640 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.9160. Min Act: -0.0001

Data Index: 776778 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.9212. Min Act: -0.0001

Data Index: 1308747 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.8894. Min Act: -0.0001

Data Index: 1452251 (Python Code)

Max Activating Token Index: 1013

Text #16

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.9353. Min Act: -0.0001

Data Index: 621816 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.8544. Min Act: -0.0001

Data Index: 1034025 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.8726. Min Act: -0.0001

Data Index: 288347 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 1.3544. Min Range: -1.3544

Max Act: 0.8985. Min Act: -0.0001

Data Index: 434409 (C4 (Web Text))

Max Activating Token Index: 717