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

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

Neuron 3027 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.6312. Min Act: -0.0000

Data Index: 373034 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.2732. Min Act: -0.0000

Data Index: 788400 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.2823. Min Act: -0.0000

Data Index: 278219 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.2808. Min Act: -0.0000

Data Index: 187368 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.2681. Min Act: -0.0000

Data Index: 802266 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.2687. Min Act: -0.0000

Data Index: 944916 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.2389. Min Act: -0.0000

Data Index: 911703 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.2373. Min Act: -0.0000

Data Index: 496691 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.2359. Min Act: -0.0000

Data Index: 560512 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.2168. Min Act: -0.0000

Data Index: 765673 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.2379. Min Act: -0.0000

Data Index: 826027 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.2301. Min Act: -0.0000

Data Index: 517372 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.2214. Min Act: -0.0000

Data Index: 1346397 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.2064. Min Act: -0.0000

Data Index: 954722 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.2239. Min Act: -0.0000

Data Index: 904517 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.2097. Min Act: -0.0000

Data Index: 1110266 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.1781. Min Act: -0.0000

Data Index: 369518 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.2075. Min Act: -0.0000

Data Index: 682563 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.1972. Min Act: -0.0000

Data Index: 22436 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.6312. Min Range: -0.6312

Max Act: 0.1912. Min Act: -0.0000

Data Index: 43651 (C4 (Web Text))

Max Activating Token Index: 666