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

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

Neuron 3789 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6658. Min Range: -4.6658

Max Act: 4.6658. Min Act: -0.0000

Data Index: 1302441 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 4.6658. Min Range: -4.6658

Max Act: 4.3372. Min Act: -0.0000

Data Index: 252510 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 4.6658. Min Range: -4.6658

Max Act: 4.1760. Min Act: -0.0000

Data Index: 1068432 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 4.6658. Min Range: -4.6658

Max Act: 4.0511. Min Act: -0.0000

Data Index: 712408 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 4.6658. Min Range: -4.6658

Max Act: 3.8226. Min Act: -0.0000

Data Index: 555530 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 4.6658. Min Range: -4.6658

Max Act: 3.8011. Min Act: -0.0000

Data Index: 156124 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 4.6658. Min Range: -4.6658

Max Act: 3.7712. Min Act: -0.0000

Data Index: 1274207 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 4.6658. Min Range: -4.6658

Max Act: 3.7420. Min Act: -0.0000

Data Index: 156265 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 4.6658. Min Range: -4.6658

Max Act: 3.7266. Min Act: -0.0000

Data Index: 1096336 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 4.6658. Min Range: -4.6658

Max Act: 3.8837. Min Act: -0.0000

Data Index: 868104 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 4.6658. Min Range: -4.6658

Max Act: 3.6903. Min Act: -0.0000

Data Index: 841129 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 4.6658. Min Range: -4.6658

Max Act: 3.6414. Min Act: -0.0000

Data Index: 978205 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 4.6658. Min Range: -4.6658

Max Act: 3.4656. Min Act: -0.0000

Data Index: 1219060 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 4.6658. Min Range: -4.6658

Max Act: 3.5805. Min Act: -0.0000

Data Index: 1294875 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 4.6658. Min Range: -4.6658

Max Act: 3.4322. Min Act: -0.0000

Data Index: 1324668 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 4.6658. Min Range: -4.6658

Max Act: 3.4417. Min Act: -0.0000

Data Index: 1208244 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 4.6658. Min Range: -4.6658

Max Act: 3.5451. Min Act: -0.0000

Data Index: 264500 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 4.6658. Min Range: -4.6658

Max Act: 3.1956. Min Act: -0.0000

Data Index: 319773 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 4.6658. Min Range: -4.6658

Max Act: 3.1842. Min Act: -0.0000

Data Index: 1013275 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 4.6658. Min Range: -4.6658

Max Act: 3.2645. Min Act: -0.0000

Data Index: 186253 (C4 (Web Text))

Max Activating Token Index: 916