Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3459 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.3373. Min Act: -0.0001

Data Index: 648244 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1305679 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1135353 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.2876. Min Act: -0.0000

Data Index: 605445 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.2748. Min Act: -0.0000

Data Index: 66020 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.2590. Min Act: -0.0000

Data Index: 520414 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.2666. Min Act: 0.0000

Data Index: 580073 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.2621. Min Act: -0.0000

Data Index: 707147 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.2573. Min Act: -0.0001

Data Index: 50089 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.2509. Min Act: -0.0000

Data Index: 1172537 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.2494. Min Act: -0.0001

Data Index: 806200 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.2499. Min Act: 0.0000

Data Index: 953890 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.2465. Min Act: -0.0001

Data Index: 1355331 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.2439. Min Act: -0.0000

Data Index: 1137876 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.2411. Min Act: -0.0000

Data Index: 402689 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.2400. Min Act: -0.0001

Data Index: 537097 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.2461. Min Act: -0.0000

Data Index: 303788 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.2286. Min Act: -0.0001

Data Index: 247980 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.2259. Min Act: -0.0000

Data Index: 79674 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.3373. Min Range: -0.3373

Max Act: 0.2259. Min Act: -0.0000

Data Index: 808878 (C4 (Web Text))

Max Activating Token Index: 540