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

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

Neuron 5641 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0466. Min Range: -4.0466

Max Act: 4.0466. Min Act: -0.0000

Data Index: 1056361 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 4.0466. Min Range: -4.0466

Max Act: 2.9548. Min Act: -0.0000

Data Index: 1155890 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 4.0466. Min Range: -4.0466

Max Act: 2.4642. Min Act: -0.0000

Data Index: 561610 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 4.0466. Min Range: -4.0466

Max Act: 2.2389. Min Act: -0.0000

Data Index: 1184316 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 4.0466. Min Range: -4.0466

Max Act: 2.2779. Min Act: -0.0000

Data Index: 1304705 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 4.0466. Min Range: -4.0466

Max Act: 2.1248. Min Act: -0.0000

Data Index: 812169 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 4.0466. Min Range: -4.0466

Max Act: 2.1034. Min Act: -0.0000

Data Index: 64533 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 4.0466. Min Range: -4.0466

Max Act: 2.1986. Min Act: -0.0000

Data Index: 423660 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 4.0466. Min Range: -4.0466

Max Act: 2.1923. Min Act: -0.0000

Data Index: 1175469 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 4.0466. Min Range: -4.0466

Max Act: 2.0437. Min Act: -0.0000

Data Index: 447367 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 4.0466. Min Range: -4.0466

Max Act: 2.1142. Min Act: -0.0000

Data Index: 508053 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 4.0466. Min Range: -4.0466

Max Act: 2.0583. Min Act: -0.0000

Data Index: 196698 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 4.0466. Min Range: -4.0466

Max Act: 2.0391. Min Act: -0.0000

Data Index: 677646 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 4.0466. Min Range: -4.0466

Max Act: 1.9201. Min Act: -0.0000

Data Index: 485723 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 4.0466. Min Range: -4.0466

Max Act: 1.8741. Min Act: -0.0000

Data Index: 603284 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 4.0466. Min Range: -4.0466

Max Act: 1.8512. Min Act: -0.0000

Data Index: 91215 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 4.0466. Min Range: -4.0466

Max Act: 1.9424. Min Act: -0.0000

Data Index: 1170951 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 4.0466. Min Range: -4.0466

Max Act: 1.8393. Min Act: -0.0000

Data Index: 471756 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 4.0466. Min Range: -4.0466

Max Act: 1.8861. Min Act: -0.0000

Data Index: 143162 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 4.0466. Min Range: -4.0466

Max Act: 1.9906. Min Act: -0.0000

Data Index: 971755 (C4 (Web Text))

Max Activating Token Index: 474