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

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

Neuron 2791 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: 2.0186. Min Range: -2.0186

Max Act: 2.0186. Min Act: -0.0000

Data Index: 1136515 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.5841. Min Act: -0.0000

Data Index: 1016292 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.2937. Min Act: -0.0000

Data Index: 996248 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.2762. Min Act: -0.0000

Data Index: 634099 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.3574. Min Act: -0.0000

Data Index: 248360 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.4815. Min Act: -0.0000

Data Index: 422754 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.3970. Min Act: -0.0000

Data Index: 520627 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.4760. Min Act: -0.0000

Data Index: 1327579 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.3616. Min Act: -0.0000

Data Index: 323006 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.3600. Min Act: -0.0000

Data Index: 1148701 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.3659. Min Act: -0.0000

Data Index: 681732 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.2627. Min Act: -0.0000

Data Index: 355103 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.2585. Min Act: -0.0000

Data Index: 390493 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.3842. Min Act: -0.0000

Data Index: 734369 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.2209. Min Act: -0.0000

Data Index: 882194 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.2896. Min Act: -0.0000

Data Index: 990467 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.3542. Min Act: -0.0000

Data Index: 444512 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.2733. Min Act: -0.0000

Data Index: 405491 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.2475. Min Act: -0.0000

Data Index: 949643 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 2.0186. Min Range: -2.0186

Max Act: 1.3177. Min Act: -0.0000

Data Index: 201056 (C4 (Web Text))

Max Activating Token Index: 769