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

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

Neuron 1863 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2578. Min Act: -0.0001

Data Index: 682757 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2615. Min Act: -0.0001

Data Index: 1172461 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2672. Min Act: -0.0001

Data Index: 844557 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2093. Min Act: -0.0001

Data Index: 1059472 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2441. Min Act: -0.0001

Data Index: 273288 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2331. Min Act: -0.0001

Data Index: 778102 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2504. Min Act: -0.0001

Data Index: 565083 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2559. Min Act: -0.0001

Data Index: 1283310 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2469. Min Act: -0.0001

Data Index: 903392 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2187. Min Act: -0.0001

Data Index: 865553 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2423. Min Act: -0.0001

Data Index: 371416 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1992. Min Act: -0.0001

Data Index: 1067841 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2398. Min Act: -0.0001

Data Index: 525025 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2426. Min Act: -0.0001

Data Index: 540186 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2211. Min Act: -0.0001

Data Index: 429528 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2392. Min Act: -0.0001

Data Index: 686793 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2201. Min Act: -0.0001

Data Index: 1098704 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2180. Min Act: -0.0001

Data Index: 822687 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2310. Min Act: -0.0001

Data Index: 1335036 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2248. Min Act: -0.0001

Data Index: 5069 (C4 (Web Text))

Max Activating Token Index: 115