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

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

Neuron 3471 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.9337. Min Act: -0.0000

Data Index: 1536073 (Python Code)

Max Activating Token Index: 222

Text #1

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.9300. Min Act: -0.0000

Data Index: 1165019 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.8217. Min Act: -0.0000

Data Index: 1390332 (Python Code)

Max Activating Token Index: 814

Text #3

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.8059. Min Act: -0.0000

Data Index: 1566924 (Python Code)

Max Activating Token Index: 340

Text #4

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.8919. Min Act: -0.0000

Data Index: 1581433 (Python Code)

Max Activating Token Index: 400

Text #5

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.8328. Min Act: -0.0000

Data Index: 1302203 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.7364. Min Act: -0.0000

Data Index: 422776 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.7233. Min Act: -0.0000

Data Index: 735050 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.6980. Min Act: -0.0000

Data Index: 1608348 (Python Code)

Max Activating Token Index: 753

Text #9

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.6502. Min Act: -0.0000

Data Index: 557793 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.5758. Min Act: -0.0000

Data Index: 1023779 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.5278. Min Act: -0.0000

Data Index: 990249 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.6013. Min Act: -0.0000

Data Index: 1478420 (Python Code)

Max Activating Token Index: 134

Text #13

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.6202. Min Act: -0.0000

Data Index: 773095 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.5265. Min Act: -0.0000

Data Index: 56202 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.5687. Min Act: -0.0000

Data Index: 1192702 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.5522. Min Act: -0.0000

Data Index: 214118 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.5288. Min Act: -0.0000

Data Index: 19948 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.4860. Min Act: -0.0000

Data Index: 1212166 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 1.9337. Min Range: -1.9337

Max Act: 1.5617. Min Act: -0.0000

Data Index: 1211565 (C4 (Web Text))

Max Activating Token Index: 365