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

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

Neuron 3003 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.3451. Min Act: -0.0001

Data Index: 607023 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.3306. Min Act: -0.0001

Data Index: 1046217 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.3075. Min Act: -0.0001

Data Index: 1055621 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2962. Min Act: -0.0001

Data Index: 1324127 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.3051. Min Act: -0.0001

Data Index: 220049 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.3034. Min Act: -0.0001

Data Index: 1004694 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2761. Min Act: -0.0001

Data Index: 478095 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2332. Min Act: -0.0001

Data Index: 1424522 (Python Code)

Max Activating Token Index: 318

Text #8

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2835. Min Act: -0.0001

Data Index: 546993 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2841. Min Act: -0.0001

Data Index: 782099 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2665. Min Act: -0.0001

Data Index: 99051 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2850. Min Act: -0.0001

Data Index: 1647035 (Python Code)

Max Activating Token Index: 492

Text #12

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2722. Min Act: -0.0001

Data Index: 1610840 (Python Code)

Max Activating Token Index: 868

Text #13

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2341. Min Act: -0.0001

Data Index: 1417365 (Python Code)

Max Activating Token Index: 838

Text #14

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2492. Min Act: -0.0001

Data Index: 1447693 (Python Code)

Max Activating Token Index: 1000

Text #15

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2320. Min Act: -0.0001

Data Index: 542378 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2559. Min Act: -0.0001

Data Index: 358843 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2628. Min Act: -0.0001

Data Index: 1629745 (Python Code)

Max Activating Token Index: 145

Text #18

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2700. Min Act: -0.0001

Data Index: 203058 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2551. Min Act: -0.0001

Data Index: 1381832 (Python Code)

Max Activating Token Index: 14