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

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

Neuron 3958 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.3906. Min Act: -0.0000

Data Index: 333800 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.1646. Min Act: 0.0000

Data Index: 981433 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.1952. Min Act: -0.0000

Data Index: 1339659 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.1066. Min Act: -0.0000

Data Index: 155024 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.1749. Min Act: -0.0000

Data Index: 1250154 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 1.3906. Min Range: -1.3906

Max Act: 0.9619. Min Act: -0.0000

Data Index: 455111 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.0148. Min Act: -0.0000

Data Index: 44596 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 1.3906. Min Range: -1.3906

Max Act: 1.0415. Min Act: -0.0000

Data Index: 337975 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 1.3906. Min Range: -1.3906

Max Act: 0.9079. Min Act: -0.0000

Data Index: 15706 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 1.3906. Min Range: -1.3906

Max Act: 0.9125. Min Act: -0.0000

Data Index: 1265646 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 1.3906. Min Range: -1.3906

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1147249 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 1.3906. Min Range: -1.3906

Max Act: 0.8725. Min Act: -0.0000

Data Index: 1285756 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 1.3906. Min Range: -1.3906

Max Act: 0.7683. Min Act: -0.0000

Data Index: 1309609 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 1.3906. Min Range: -1.3906

Max Act: 0.8792. Min Act: -0.0000

Data Index: 1200886 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 1.3906. Min Range: -1.3906

Max Act: 0.7420. Min Act: -0.0000

Data Index: 636672 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 1.3906. Min Range: -1.3906

Max Act: 0.7560. Min Act: -0.0000

Data Index: 195749 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 1.3906. Min Range: -1.3906

Max Act: 0.7212. Min Act: -0.0000

Data Index: 284323 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 1.3906. Min Range: -1.3906

Max Act: 0.6865. Min Act: -0.0000

Data Index: 299979 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 1.3906. Min Range: -1.3906

Max Act: 0.6231. Min Act: -0.0000

Data Index: 1038384 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 1.3906. Min Range: -1.3906

Max Act: 0.5648. Min Act: -0.0000

Data Index: 41080 (C4 (Web Text))

Max Activating Token Index: 242