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

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

Neuron 4820 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: 3.2944. Min Range: -3.2944

Max Act: 3.2313. Min Act: -0.0000

Data Index: 24759 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 3.2944. Min Range: -3.2944

Max Act: 3.2944. Min Act: -0.0000

Data Index: 1356816 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.9702. Min Act: -0.0000

Data Index: 425865 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.8433. Min Act: -0.0000

Data Index: 955610 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.9915. Min Act: -0.0000

Data Index: 635394 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.9283. Min Act: -0.0000

Data Index: 888584 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.8227. Min Act: -0.0000

Data Index: 876652 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.8728. Min Act: -0.0000

Data Index: 1384019 (Python Code)

Max Activating Token Index: 875

Text #8

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.7448. Min Act: -0.0000

Data Index: 1006801 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.7444. Min Act: -0.0001

Data Index: 1608156 (Python Code)

Max Activating Token Index: 745

Text #10

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.5880. Min Act: -0.0000

Data Index: 515431 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.7001. Min Act: -0.0000

Data Index: 214494 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.5262. Min Act: -0.0000

Data Index: 531275 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.5083. Min Act: -0.0000

Data Index: 126549 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.4043. Min Act: -0.0000

Data Index: 559596 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.5092. Min Act: -0.0000

Data Index: 552702 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.4850. Min Act: -0.0000

Data Index: 1033844 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.6124. Min Act: -0.0000

Data Index: 853297 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.4725. Min Act: -0.0000

Data Index: 986412 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 3.2944. Min Range: -3.2944

Max Act: 2.4210. Min Act: -0.0000

Data Index: 915574 (C4 (Web Text))

Max Activating Token Index: 397