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

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

Neuron 691 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2296. Min Range: -1.2296

Max Act: 1.2296. Min Act: -0.0000

Data Index: 582336 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 1.2296. Min Range: -1.2296

Max Act: 1.0599. Min Act: -0.0000

Data Index: 65843 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 1.2296. Min Range: -1.2296

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1004801 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9900. Min Act: -0.0000

Data Index: 379607 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 1.2296. Min Range: -1.2296

Max Act: 1.1236. Min Act: -0.0000

Data Index: 739275 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9796. Min Act: -0.0000

Data Index: 1192595 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9538. Min Act: -0.0000

Data Index: 1347284 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9349. Min Act: -0.0000

Data Index: 932672 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9208. Min Act: -0.0000

Data Index: 831638 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8252. Min Act: -0.0000

Data Index: 1057111 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9265. Min Act: -0.0000

Data Index: 1461582 (Python Code)

Max Activating Token Index: 522

Text #11

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9077. Min Act: -0.0000

Data Index: 251805 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8950. Min Act: -0.0000

Data Index: 545521 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9787. Min Act: -0.0000

Data Index: 515913 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 1.2296. Min Range: -1.2296

Max Act: 1.0172. Min Act: -0.0000

Data Index: 220158 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8535. Min Act: -0.0000

Data Index: 963892 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9407. Min Act: -0.0000

Data Index: 985026 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8516. Min Act: -0.0000

Data Index: 554656 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.8252. Min Act: -0.0000

Data Index: 956882 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 1.2296. Min Range: -1.2296

Max Act: 0.9241. Min Act: -0.0000

Data Index: 425986 (C4 (Web Text))

Max Activating Token Index: 535