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

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

Neuron 3665 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: 3.8544. Min Range: -3.8544

Max Act: 3.8544. Min Act: -0.0000

Data Index: 1145324 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 3.8544. Min Range: -3.8544

Max Act: 3.5296. Min Act: -0.0000

Data Index: 505322 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 3.8544. Min Range: -3.8544

Max Act: 3.2252. Min Act: -0.0000

Data Index: 1303113 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 3.8544. Min Range: -3.8544

Max Act: 2.8906. Min Act: -0.0000

Data Index: 745171 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 3.8544. Min Range: -3.8544

Max Act: 3.0632. Min Act: -0.0000

Data Index: 530544 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 3.8544. Min Range: -3.8544

Max Act: 2.8198. Min Act: -0.0000

Data Index: 203971 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 3.8544. Min Range: -3.8544

Max Act: 2.7394. Min Act: -0.0000

Data Index: 1066040 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 3.8544. Min Range: -3.8544

Max Act: 2.9359. Min Act: -0.0000

Data Index: 146532 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 3.8544. Min Range: -3.8544

Max Act: 2.3815. Min Act: -0.0000

Data Index: 200302 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 3.8544. Min Range: -3.8544

Max Act: 2.7341. Min Act: -0.0000

Data Index: 93100 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 3.8544. Min Range: -3.8544

Max Act: 2.4494. Min Act: -0.0000

Data Index: 684072 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 3.8544. Min Range: -3.8544

Max Act: 2.6071. Min Act: -0.0000

Data Index: 1015646 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 3.8544. Min Range: -3.8544

Max Act: 2.8746. Min Act: -0.0000

Data Index: 867635 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 3.8544. Min Range: -3.8544

Max Act: 2.5478. Min Act: -0.0000

Data Index: 1257071 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 3.8544. Min Range: -3.8544

Max Act: 2.9366. Min Act: -0.0000

Data Index: 1231367 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 3.8544. Min Range: -3.8544

Max Act: 2.5310. Min Act: -0.0000

Data Index: 325601 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 3.8544. Min Range: -3.8544

Max Act: 2.3863. Min Act: -0.0000

Data Index: 1490681 (Python Code)

Max Activating Token Index: 193

Text #17

Max Range: 3.8544. Min Range: -3.8544

Max Act: 2.3360. Min Act: -0.0000

Data Index: 369239 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 3.8544. Min Range: -3.8544

Max Act: 2.4425. Min Act: -0.0000

Data Index: 370701 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 3.8544. Min Range: -3.8544

Max Act: 2.5890. Min Act: -0.0000

Data Index: 279740 (C4 (Web Text))

Max Activating Token Index: 726