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

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

Neuron 100 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: 0.0458. Min Range: -0.0458

Max Act: 0.0458. Min Act: -0.0004

Data Index: 1242579 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0407. Min Act: -0.0004

Data Index: 673586 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0393. Min Act: -0.0004

Data Index: 456605 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0400. Min Act: -0.0004

Data Index: 561841 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0389. Min Act: -0.0004

Data Index: 229777 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0395. Min Act: -0.0004

Data Index: 894539 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0402. Min Act: -0.0004

Data Index: 474153 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0381. Min Act: -0.0004

Data Index: 1323222 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0360. Min Act: -0.0004

Data Index: 1231702 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0360. Min Act: -0.0004

Data Index: 8341 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0384. Min Act: -0.0004

Data Index: 924073 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0358. Min Act: -0.0004

Data Index: 885083 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0349. Min Act: -0.0004

Data Index: 1178718 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0381. Min Act: -0.0004

Data Index: 1032056 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0360. Min Act: -0.0004

Data Index: 1351953 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0342. Min Act: -0.0004

Data Index: 1269420 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0348. Min Act: -0.0004

Data Index: 1128891 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0364. Min Act: -0.0004

Data Index: 812720 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0354. Min Act: -0.0004

Data Index: 494920 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0339. Min Act: -0.0004

Data Index: 1086458 (C4 (Web Text))

Max Activating Token Index: 359