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

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

Neuron 2042 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.8586. Min Act: -0.0000

Data Index: 1004132 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.9334. Min Act: -0.0000

Data Index: 996140 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.8161. Min Act: -0.0000

Data Index: 1428558 (Python Code)

Max Activating Token Index: 769

Text #3

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.8281. Min Act: -0.0000

Data Index: 1644912 (Python Code)

Max Activating Token Index: 804

Text #4

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1362662 (Python Code)

Max Activating Token Index: 414

Text #5

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1569401 (Python Code)

Max Activating Token Index: 458

Text #6

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.8332. Min Act: -0.0000

Data Index: 1593230 (Python Code)

Max Activating Token Index: 44

Text #7

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1517595 (Python Code)

Max Activating Token Index: 597

Text #8

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.7258. Min Act: -0.0000

Data Index: 1363182 (Python Code)

Max Activating Token Index: 308

Text #9

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.6805. Min Act: -0.0000

Data Index: 1597848 (Python Code)

Max Activating Token Index: 563

Text #10

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1389077 (Python Code)

Max Activating Token Index: 326

Text #11

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1484739 (Python Code)

Max Activating Token Index: 544

Text #12

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.6205. Min Act: -0.0000

Data Index: 1417230 (Python Code)

Max Activating Token Index: 782

Text #13

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1440512 (Python Code)

Max Activating Token Index: 499

Text #14

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.6890. Min Act: -0.0000

Data Index: 1432757 (Python Code)

Max Activating Token Index: 1000

Text #15

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.6474. Min Act: -0.0000

Data Index: 1512616 (Python Code)

Max Activating Token Index: 750

Text #16

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1474350 (Python Code)

Max Activating Token Index: 981

Text #17

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.6775. Min Act: -0.0000

Data Index: 1361702 (Python Code)

Max Activating Token Index: 186

Text #18

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1561109 (Python Code)

Max Activating Token Index: 282

Text #19

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1639536 (Python Code)

Max Activating Token Index: 892