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

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

Neuron 1277 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3299. Min Range: -1.3299

Max Act: 1.3299. Min Act: -0.0000

Data Index: 750394 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 1.3299. Min Range: -1.3299

Max Act: 0.9686. Min Act: -0.0001

Data Index: 1583196 (Python Code)

Max Activating Token Index: 715

Text #2

Max Range: 1.3299. Min Range: -1.3299

Max Act: 1.0887. Min Act: -0.0001

Data Index: 496222 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 1.3299. Min Range: -1.3299

Max Act: 0.9821. Min Act: -0.0001

Data Index: 525046 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 1.3299. Min Range: -1.3299

Max Act: 0.9454. Min Act: -0.0001

Data Index: 829255 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 1.3299. Min Range: -1.3299

Max Act: 0.8707. Min Act: -0.0001

Data Index: 1619718 (Python Code)

Max Activating Token Index: 305

Text #6

Max Range: 1.3299. Min Range: -1.3299

Max Act: 0.9620. Min Act: -0.0001

Data Index: 959998 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 1.3299. Min Range: -1.3299

Max Act: 0.9486. Min Act: -0.0001

Data Index: 117114 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 1.3299. Min Range: -1.3299

Max Act: 0.9990. Min Act: -0.0001

Data Index: 225142 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 1.3299. Min Range: -1.3299

Max Act: 0.9686. Min Act: -0.0001

Data Index: 535862 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 1.3299. Min Range: -1.3299

Max Act: 0.8519. Min Act: -0.0001

Data Index: 671137 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 1.3299. Min Range: -1.3299

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1501502 (Python Code)

Max Activating Token Index: 957

Text #12

Max Range: 1.3299. Min Range: -1.3299

Max Act: 1.0245. Min Act: -0.0001

Data Index: 1093632 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 1.3299. Min Range: -1.3299

Max Act: 0.9233. Min Act: -0.0001

Data Index: 1282283 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 1.3299. Min Range: -1.3299

Max Act: 0.9179. Min Act: -0.0001

Data Index: 1090336 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 1.3299. Min Range: -1.3299

Max Act: 0.9786. Min Act: -0.0001

Data Index: 704633 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 1.3299. Min Range: -1.3299

Max Act: 0.9064. Min Act: -0.0000

Data Index: 539604 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 1.3299. Min Range: -1.3299

Max Act: 0.8799. Min Act: -0.0001

Data Index: 1072466 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 1.3299. Min Range: -1.3299

Max Act: 0.8854. Min Act: -0.0001

Data Index: 6138 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 1.3299. Min Range: -1.3299

Max Act: 0.8906. Min Act: -0.0001

Data Index: 695332 (C4 (Web Text))

Max Activating Token Index: 40