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

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

Neuron 457 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.4658. Min Act: -0.0000

Data Index: 647028 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.3304. Min Act: -0.0000

Data Index: 81191 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.3205. Min Act: -0.0000

Data Index: 19406 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1142263 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.2645. Min Act: -0.0000

Data Index: 594618 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.2720. Min Act: -0.0000

Data Index: 674067 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.2521. Min Act: -0.0000

Data Index: 1117910 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.2691. Min Act: -0.0000

Data Index: 98937 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.2475. Min Act: -0.0000

Data Index: 737968 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.2554. Min Act: -0.0000

Data Index: 311806 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.2495. Min Act: -0.0000

Data Index: 122958 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.2572. Min Act: -0.0000

Data Index: 16247 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.2470. Min Act: -0.0000

Data Index: 498497 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1140219 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.2573. Min Act: -0.0000

Data Index: 388857 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.2312. Min Act: -0.0000

Data Index: 1574766 (Python Code)

Max Activating Token Index: 536

Text #16

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1468395 (Python Code)

Max Activating Token Index: 223

Text #17

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.2406. Min Act: -0.0000

Data Index: 145320 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.2371. Min Act: -0.0000

Data Index: 851000 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.4658. Min Range: -0.4658

Max Act: 0.2456. Min Act: -0.0000

Data Index: 818943 (C4 (Web Text))

Max Activating Token Index: 147