Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4702 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2724. Min Range: -2.2724

Max Act: 2.2724. Min Act: -0.0000

Data Index: 433050 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 2.2724. Min Range: -2.2724

Max Act: 1.3760. Min Act: -0.0000

Data Index: 899589 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 2.2724. Min Range: -2.2724

Max Act: 1.3216. Min Act: -0.0000

Data Index: 386627 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 2.2724. Min Range: -2.2724

Max Act: 1.2506. Min Act: -0.0000

Data Index: 630217 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 2.2724. Min Range: -2.2724

Max Act: 1.2798. Min Act: -0.0000

Data Index: 859953 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 2.2724. Min Range: -2.2724

Max Act: 1.2057. Min Act: -0.0000

Data Index: 655810 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 2.2724. Min Range: -2.2724

Max Act: 1.2063. Min Act: -0.0000

Data Index: 1042703 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 2.2724. Min Range: -2.2724

Max Act: 1.0956. Min Act: -0.0000

Data Index: 953639 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 2.2724. Min Range: -2.2724

Max Act: 1.1499. Min Act: -0.0000

Data Index: 1208928 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 2.2724. Min Range: -2.2724

Max Act: 1.1485. Min Act: -0.0000

Data Index: 319552 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 2.2724. Min Range: -2.2724

Max Act: 1.0658. Min Act: -0.0000

Data Index: 1337211 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 2.2724. Min Range: -2.2724

Max Act: 1.1223. Min Act: -0.0000

Data Index: 1272619 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 2.2724. Min Range: -2.2724

Max Act: 0.9889. Min Act: -0.0000

Data Index: 642537 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 2.2724. Min Range: -2.2724

Max Act: 1.0398. Min Act: -0.0000

Data Index: 159371 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 2.2724. Min Range: -2.2724

Max Act: 1.0970. Min Act: -0.0000

Data Index: 698185 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 2.2724. Min Range: -2.2724

Max Act: 1.0200. Min Act: -0.0000

Data Index: 796090 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 2.2724. Min Range: -2.2724

Max Act: 0.9758. Min Act: -0.0000

Data Index: 36383 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 2.2724. Min Range: -2.2724

Max Act: 0.9957. Min Act: -0.0000

Data Index: 232553 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 2.2724. Min Range: -2.2724

Max Act: 0.9576. Min Act: -0.0000

Data Index: 727262 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 2.2724. Min Range: -2.2724

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1348600 (C4 (Web Text))

Max Activating Token Index: 292