Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1609 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.8686. Min Range: -3.8686

Max Act: 3.7528. Min Act: -0.0002

Data Index: 927828 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 3.8686. Min Range: -3.8686

Max Act: 3.6955. Min Act: -0.0001

Data Index: 624616 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 3.8686. Min Range: -3.8686

Max Act: 3.8686. Min Act: -0.0002

Data Index: 339227 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 3.8686. Min Range: -3.8686

Max Act: 3.5442. Min Act: -0.0002

Data Index: 229966 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 3.8686. Min Range: -3.8686

Max Act: 3.2647. Min Act: -0.0002

Data Index: 1232438 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 3.8686. Min Range: -3.8686

Max Act: 3.6469. Min Act: -0.0002

Data Index: 530751 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 3.8686. Min Range: -3.8686

Max Act: 3.2786. Min Act: -0.0002

Data Index: 1046926 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 3.8686. Min Range: -3.8686

Max Act: 3.1341. Min Act: -0.0002

Data Index: 257320 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 3.8686. Min Range: -3.8686

Max Act: 3.4003. Min Act: -0.0001

Data Index: 829850 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 3.8686. Min Range: -3.8686

Max Act: 3.4507. Min Act: -0.0002

Data Index: 457111 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 3.8686. Min Range: -3.8686

Max Act: 3.1614. Min Act: -0.0002

Data Index: 442880 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 3.8686. Min Range: -3.8686

Max Act: 3.4333. Min Act: -0.0002

Data Index: 642957 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 3.8686. Min Range: -3.8686

Max Act: 3.2332. Min Act: -0.0001

Data Index: 1103233 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 3.8686. Min Range: -3.8686

Max Act: 3.1427. Min Act: -0.0002

Data Index: 40798 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 3.8686. Min Range: -3.8686

Max Act: 3.2604. Min Act: -0.0002

Data Index: 693605 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 3.8686. Min Range: -3.8686

Max Act: 3.1675. Min Act: -0.0002

Data Index: 1143745 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 3.8686. Min Range: -3.8686

Max Act: 2.9825. Min Act: -0.0001

Data Index: 1311912 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 3.8686. Min Range: -3.8686

Max Act: 3.2455. Min Act: -0.0002

Data Index: 1145278 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 3.8686. Min Range: -3.8686

Max Act: 3.4090. Min Act: -0.0001

Data Index: 921108 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 3.8686. Min Range: -3.8686

Max Act: 2.8999. Min Act: -0.0002

Data Index: 151087 (C4 (Web Text))

Max Activating Token Index: 600