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

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

Neuron 1187 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.7527. Min Act: -0.0004

Data Index: 961433 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.7771. Min Act: -0.0004

Data Index: 867842 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.7682. Min Act: -0.0004

Data Index: 17625 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.7441. Min Act: -0.0004

Data Index: 530840 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.7862. Min Act: -0.0004

Data Index: 1209050 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.7397. Min Act: -0.0004

Data Index: 1285172 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.7153. Min Act: -0.0004

Data Index: 1279395 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.7597. Min Act: -0.0004

Data Index: 861751 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.7785. Min Act: -0.0004

Data Index: 156118 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.7282. Min Act: -0.0004

Data Index: 508022 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.7586. Min Act: -0.0004

Data Index: 1165312 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.6891. Min Act: -0.0004

Data Index: 282188 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.8293. Min Act: -0.0004

Data Index: 426670 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.5791. Min Act: -0.0004

Data Index: 1081214 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.7943. Min Act: -0.0004

Data Index: 578341 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.8463. Min Act: -0.0004

Data Index: 432386 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.7473. Min Act: -0.0004

Data Index: 344141 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.7018. Min Act: -0.0004

Data Index: 81448 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.7466. Min Act: -0.0004

Data Index: 294357 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.8463. Min Range: -0.8463

Max Act: 0.7356. Min Act: -0.0004

Data Index: 1182295 (C4 (Web Text))

Max Activating Token Index: 86