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

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

Neuron 118 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.2068. Min Act: -0.0001

Data Index: 489809 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1495. Min Act: -0.0001

Data Index: 456174 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1560. Min Act: -0.0001

Data Index: 287620 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1587. Min Act: -0.0001

Data Index: 61948 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1519. Min Act: -0.0001

Data Index: 299876 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1445. Min Act: -0.0001

Data Index: 496009 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1402. Min Act: -0.0001

Data Index: 571797 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1384. Min Act: -0.0001

Data Index: 234311 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1343. Min Act: -0.0001

Data Index: 1067596 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1316. Min Act: -0.0001

Data Index: 499246 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1308. Min Act: -0.0001

Data Index: 842584 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1351. Min Act: -0.0001

Data Index: 443310 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1344983 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1122. Min Act: -0.0001

Data Index: 1100035 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1234. Min Act: -0.0001

Data Index: 517783 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1281. Min Act: -0.0001

Data Index: 146559 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1343. Min Act: -0.0001

Data Index: 513101 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1106. Min Act: -0.0001

Data Index: 901256 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1161. Min Act: -0.0001

Data Index: 1609602 (Python Code)

Max Activating Token Index: 225

Text #19

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1198. Min Act: -0.0001

Data Index: 1652087 (Python Code)

Max Activating Token Index: 454