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

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

Neuron 3580 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4215. Min Range: -1.4215

Max Act: 1.4215. Min Act: -0.0000

Data Index: 1343829 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 1.4215. Min Range: -1.4215

Max Act: 1.2174. Min Act: -0.0000

Data Index: 1509931 (Python Code)

Max Activating Token Index: 903

Text #2

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.9370. Min Act: -0.0000

Data Index: 417424 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.7305. Min Act: -0.0000

Data Index: 387743 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.7242. Min Act: -0.0000

Data Index: 154295 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1477639 (Python Code)

Max Activating Token Index: 394

Text #6

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.6423. Min Act: -0.0000

Data Index: 1225102 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.6478. Min Act: -0.0000

Data Index: 879734 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.6384. Min Act: -0.0000

Data Index: 987837 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1360571 (Python Code)

Max Activating Token Index: 552

Text #10

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.6008. Min Act: -0.0000

Data Index: 172679 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.5951. Min Act: -0.0000

Data Index: 133077 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1584453 (Python Code)

Max Activating Token Index: 396

Text #13

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.4803. Min Act: -0.0000

Data Index: 1419628 (Python Code)

Max Activating Token Index: 765

Text #14

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1585280 (Python Code)

Max Activating Token Index: 706

Text #15

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.5212. Min Act: -0.0000

Data Index: 591552 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.5312. Min Act: -0.0000

Data Index: 321396 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.5431. Min Act: -0.0000

Data Index: 769375 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1362259 (Python Code)

Max Activating Token Index: 323

Text #19

Max Range: 1.4215. Min Range: -1.4215

Max Act: 0.5041. Min Act: -0.0000

Data Index: 141234 (C4 (Web Text))

Max Activating Token Index: 477