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

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

Neuron 4918 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.6292. Min Act: -0.0000

Data Index: 89575 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.4582. Min Act: -0.0000

Data Index: 506057 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.4967. Min Act: -0.0000

Data Index: 722579 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.4346. Min Act: -0.0000

Data Index: 582662 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.2806. Min Act: -0.0000

Data Index: 441189 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.2588. Min Act: -0.0000

Data Index: 889690 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.3423. Min Act: -0.0000

Data Index: 1069998 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.2600. Min Act: -0.0000

Data Index: 399906 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.3108. Min Act: -0.0000

Data Index: 1086363 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.2319. Min Act: -0.0000

Data Index: 846233 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.1137. Min Act: -0.0000

Data Index: 61828 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.1743. Min Act: -0.0000

Data Index: 778400 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.1421. Min Act: -0.0000

Data Index: 171812 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.1197. Min Act: -0.0000

Data Index: 1267050 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.0952. Min Act: -0.0000

Data Index: 976163 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.1846. Min Act: -0.0000

Data Index: 67172 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.1550. Min Act: -0.0000

Data Index: 1170333 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.0705. Min Act: -0.0000

Data Index: 205388 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.0195. Min Act: -0.0000

Data Index: 820059 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 1.6292. Min Range: -1.6292

Max Act: 1.0554. Min Act: -0.0000

Data Index: 877580 (C4 (Web Text))

Max Activating Token Index: 76