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

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

Neuron 2118 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2529. Min Range: -1.2529

Max Act: 1.2529. Min Act: -0.0000

Data Index: 793908 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 1.2529. Min Range: -1.2529

Max Act: 1.1647. Min Act: -0.0000

Data Index: 593662 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 1.2529. Min Range: -1.2529

Max Act: 1.0220. Min Act: -0.0000

Data Index: 386635 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 1.2529. Min Range: -1.2529

Max Act: 1.0582. Min Act: -0.0000

Data Index: 1185142 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 1.2529. Min Range: -1.2529

Max Act: 1.0766. Min Act: -0.0000

Data Index: 770942 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 1.2529. Min Range: -1.2529

Max Act: 1.0570. Min Act: -0.0000

Data Index: 668148 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 1.2529. Min Range: -1.2529

Max Act: 1.1230. Min Act: -0.0000

Data Index: 729135 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 1.2529. Min Range: -1.2529

Max Act: 1.0424. Min Act: -0.0000

Data Index: 218731 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 1.2529. Min Range: -1.2529

Max Act: 0.9790. Min Act: -0.0000

Data Index: 279749 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 1.2529. Min Range: -1.2529

Max Act: 0.9408. Min Act: -0.0000

Data Index: 1194231 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 1.2529. Min Range: -1.2529

Max Act: 0.8494. Min Act: -0.0000

Data Index: 1019331 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 1.2529. Min Range: -1.2529

Max Act: 1.0030. Min Act: -0.0000

Data Index: 459204 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 1.2529. Min Range: -1.2529

Max Act: 0.9275. Min Act: -0.0000

Data Index: 902471 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 1.2529. Min Range: -1.2529

Max Act: 0.9414. Min Act: -0.0000

Data Index: 453515 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 1.2529. Min Range: -1.2529

Max Act: 0.9551. Min Act: -0.0000

Data Index: 10490 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 1.2529. Min Range: -1.2529

Max Act: 0.8969. Min Act: -0.0000

Data Index: 869927 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 1.2529. Min Range: -1.2529

Max Act: 0.8932. Min Act: -0.0000

Data Index: 689125 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 1.2529. Min Range: -1.2529

Max Act: 0.8820. Min Act: -0.0000

Data Index: 998629 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 1.2529. Min Range: -1.2529

Max Act: 0.8977. Min Act: -0.0000

Data Index: 1283800 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 1.2529. Min Range: -1.2529

Max Act: 0.9003. Min Act: -0.0000

Data Index: 309669 (C4 (Web Text))

Max Activating Token Index: 437