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

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

Neuron 908 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: 1.8210. Min Range: -1.8210

Max Act: 1.8210. Min Act: -0.0001

Data Index: 940926 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.4650. Min Act: -0.0001

Data Index: 1143913 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.4296. Min Act: -0.0002

Data Index: 921422 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.3604. Min Act: -0.0002

Data Index: 1272522 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.3747. Min Act: -0.0002

Data Index: 316967 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.2804. Min Act: -0.0002

Data Index: 321893 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.3057. Min Act: -0.0002

Data Index: 883963 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.3712. Min Act: -0.0002

Data Index: 985670 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.3634. Min Act: -0.0002

Data Index: 1133548 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.4342. Min Act: -0.0002

Data Index: 741379 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.3171. Min Act: -0.0002

Data Index: 1133840 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.3042. Min Act: -0.0002

Data Index: 434552 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.3362. Min Act: -0.0002

Data Index: 546693 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.1712. Min Act: -0.0002

Data Index: 1023112 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.3245. Min Act: -0.0002

Data Index: 1075480 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.2897. Min Act: -0.0001

Data Index: 921703 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.3240. Min Act: -0.0002

Data Index: 807538 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.2369. Min Act: -0.0002

Data Index: 960526 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.1989. Min Act: -0.0002

Data Index: 921704 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 1.8210. Min Range: -1.8210

Max Act: 1.2250. Min Act: -0.0002

Data Index: 760522 (C4 (Web Text))

Max Activating Token Index: 491