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

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

Neuron 1306 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.8834. Min Act: -0.0003

Data Index: 944517 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.8077. Min Act: -0.0003

Data Index: 1261407 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7842. Min Act: -0.0003

Data Index: 316930 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7723. Min Act: -0.0003

Data Index: 18025 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.8039. Min Act: -0.0003

Data Index: 301624 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7455. Min Act: -0.0003

Data Index: 487109 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7919. Min Act: -0.0003

Data Index: 623207 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7348. Min Act: -0.0003

Data Index: 1059383 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7590. Min Act: -0.0003

Data Index: 544023 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7522. Min Act: -0.0003

Data Index: 594986 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7262. Min Act: -0.0003

Data Index: 956259 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7186. Min Act: -0.0003

Data Index: 1296198 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.6746. Min Act: -0.0003

Data Index: 1256273 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7406. Min Act: -0.0003

Data Index: 725251 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7097. Min Act: -0.0003

Data Index: 902972 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.6643. Min Act: -0.0003

Data Index: 179971 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.6667. Min Act: -0.0003

Data Index: 1155380 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.6775. Min Act: -0.0003

Data Index: 930295 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.6374. Min Act: -0.0003

Data Index: 712855 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.6807. Min Act: -0.0003

Data Index: 223987 (C4 (Web Text))

Max Activating Token Index: 777