Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1869 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.8307. Min Act: -0.0001

Data Index: 187433 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.7363. Min Act: -0.0001

Data Index: 1168386 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.6417. Min Act: -0.0001

Data Index: 95326 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.6151. Min Act: -0.0001

Data Index: 346230 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5927. Min Act: -0.0001

Data Index: 1271106 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5354. Min Act: -0.0001

Data Index: 725603 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5505. Min Act: -0.0001

Data Index: 378315 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5458. Min Act: -0.0001

Data Index: 999477 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4665. Min Act: -0.0001

Data Index: 521930 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5370. Min Act: -0.0001

Data Index: 905085 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4956. Min Act: -0.0001

Data Index: 1281197 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5541. Min Act: -0.0001

Data Index: 786190 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5161. Min Act: -0.0001

Data Index: 737235 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4634. Min Act: -0.0001

Data Index: 816306 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4748. Min Act: -0.0001

Data Index: 167902 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5298. Min Act: -0.0001

Data Index: 1286920 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4814. Min Act: -0.0001

Data Index: 1072823 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4773. Min Act: -0.0001

Data Index: 125346 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4583. Min Act: -0.0001

Data Index: 161475 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.4553. Min Act: -0.0001

Data Index: 215527 (C4 (Web Text))

Max Activating Token Index: 472