Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1605 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.4214. Min Act: -0.0003

Data Index: 1416571 (Python Code)

Max Activating Token Index: 738

Text #1

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3527. Min Act: -0.0003

Data Index: 1511983 (Python Code)

Max Activating Token Index: 844

Text #2

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3743. Min Act: -0.0003

Data Index: 1531689 (Python Code)

Max Activating Token Index: 785

Text #3

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3627. Min Act: -0.0003

Data Index: 1557816 (Python Code)

Max Activating Token Index: 938

Text #4

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3472. Min Act: -0.0004

Data Index: 643704 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3583. Min Act: -0.0003

Data Index: 1496750 (Python Code)

Max Activating Token Index: 717

Text #6

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3278. Min Act: -0.0003

Data Index: 1588616 (Python Code)

Max Activating Token Index: 601

Text #7

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3150. Min Act: -0.0003

Data Index: 1128366 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3399. Min Act: -0.0003

Data Index: 1430484 (Python Code)

Max Activating Token Index: 713

Text #9

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3293. Min Act: -0.0003

Data Index: 1397972 (Python Code)

Max Activating Token Index: 298

Text #10

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3250. Min Act: -0.0003

Data Index: 1563611 (Python Code)

Max Activating Token Index: 731

Text #11

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3236. Min Act: -0.0003

Data Index: 1374343 (Python Code)

Max Activating Token Index: 718

Text #12

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3191. Min Act: -0.0002

Data Index: 1555446 (Python Code)

Max Activating Token Index: 587

Text #13

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3075. Min Act: -0.0003

Data Index: 1485399 (Python Code)

Max Activating Token Index: 899

Text #14

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3169. Min Act: -0.0003

Data Index: 1375202 (Python Code)

Max Activating Token Index: 147

Text #15

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3233. Min Act: -0.0003

Data Index: 1396157 (Python Code)

Max Activating Token Index: 669

Text #16

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3120. Min Act: -0.0003

Data Index: 1401675 (Python Code)

Max Activating Token Index: 788

Text #17

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3055. Min Act: -0.0003

Data Index: 1362109 (Python Code)

Max Activating Token Index: 109

Text #18

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3167. Min Act: -0.0003

Data Index: 1450124 (Python Code)

Max Activating Token Index: 82

Text #19

Max Range: 0.4214. Min Range: -0.4214

Max Act: 0.3035. Min Act: -0.0003

Data Index: 1591141 (Python Code)

Max Activating Token Index: 347