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

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

Neuron 2039 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0606. Min Act: -0.0002

Data Index: 617225 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0597. Min Act: -0.0002

Data Index: 819354 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1289677 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0593. Min Act: -0.0002

Data Index: 770197 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0587. Min Act: -0.0002

Data Index: 709561 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0579. Min Act: -0.0002

Data Index: 972482 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1307773 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1297178 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0570. Min Act: -0.0002

Data Index: 521703 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1144474 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1089472 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0546. Min Act: -0.0002

Data Index: 794440 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0558. Min Act: -0.0002

Data Index: 620970 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0535. Min Act: -0.0002

Data Index: 646129 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0535. Min Act: -0.0002

Data Index: 623029 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1218291 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0548. Min Act: -0.0002

Data Index: 853332 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0542. Min Act: -0.0002

Data Index: 641294 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1494333 (Python Code)

Max Activating Token Index: 195

Text #19

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1095595 (C4 (Web Text))

Max Activating Token Index: 179