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

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

Neuron 1893 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0560. Min Act: -0.0001

Data Index: 965375 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0622. Min Act: -0.0001

Data Index: 516396 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0525. Min Act: -0.0001

Data Index: 340905 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1506962 (Python Code)

Max Activating Token Index: 815

Text #4

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0489. Min Act: -0.0001

Data Index: 867146 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0506. Min Act: -0.0001

Data Index: 606400 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0490. Min Act: -0.0001

Data Index: 197418 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0419. Min Act: -0.0001

Data Index: 4071 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0467. Min Act: -0.0001

Data Index: 256572 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0433. Min Act: -0.0001

Data Index: 62639 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0454. Min Act: -0.0001

Data Index: 959319 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0450. Min Act: -0.0001

Data Index: 1451472 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0411. Min Act: -0.0001

Data Index: 1393935 (Python Code)

Max Activating Token Index: 555

Text #13

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0442. Min Act: -0.0001

Data Index: 1241831 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0446. Min Act: -0.0001

Data Index: 1465878 (Python Code)

Max Activating Token Index: 363

Text #15

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0499. Min Act: -0.0001

Data Index: 1065142 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0412. Min Act: -0.0001

Data Index: 849969 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0439. Min Act: -0.0001

Data Index: 1166826 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0421. Min Act: -0.0001

Data Index: 233424 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0423. Min Act: -0.0001

Data Index: 391551 (C4 (Web Text))

Max Activating Token Index: 418