Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4565 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0058. Min Range: -2.0058

Max Act: 2.0018. Min Act: -0.0000

Data Index: 1301165 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 2.0058. Min Range: -2.0058

Max Act: 2.0058. Min Act: -0.0000

Data Index: 910170 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 2.0058. Min Range: -2.0058

Max Act: 1.6440. Min Act: -0.0000

Data Index: 886100 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 2.0058. Min Range: -2.0058

Max Act: 1.6036. Min Act: -0.0000

Data Index: 1129469 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 2.0058. Min Range: -2.0058

Max Act: 1.4432. Min Act: -0.0000

Data Index: 721863 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 2.0058. Min Range: -2.0058

Max Act: 1.5256. Min Act: -0.0000

Data Index: 1289180 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 2.0058. Min Range: -2.0058

Max Act: 1.4194. Min Act: -0.0000

Data Index: 787297 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 2.0058. Min Range: -2.0058

Max Act: 1.3615. Min Act: -0.0000

Data Index: 375922 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 2.0058. Min Range: -2.0058

Max Act: 1.2846. Min Act: -0.0000

Data Index: 840299 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 2.0058. Min Range: -2.0058

Max Act: 1.2667. Min Act: -0.0000

Data Index: 1314055 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 2.0058. Min Range: -2.0058

Max Act: 1.2907. Min Act: -0.0000

Data Index: 1179176 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 2.0058. Min Range: -2.0058

Max Act: 1.2950. Min Act: -0.0000

Data Index: 1188146 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 2.0058. Min Range: -2.0058

Max Act: 1.2663. Min Act: -0.0000

Data Index: 1190070 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 2.0058. Min Range: -2.0058

Max Act: 1.3052. Min Act: -0.0000

Data Index: 964425 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 2.0058. Min Range: -2.0058

Max Act: 1.2785. Min Act: -0.0000

Data Index: 861566 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 2.0058. Min Range: -2.0058

Max Act: 1.2393. Min Act: -0.0000

Data Index: 222525 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 2.0058. Min Range: -2.0058

Max Act: 1.2743. Min Act: -0.0000

Data Index: 1226285 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 2.0058. Min Range: -2.0058

Max Act: 1.2581. Min Act: -0.0000

Data Index: 1288297 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 2.0058. Min Range: -2.0058

Max Act: 1.1999. Min Act: -0.0000

Data Index: 402434 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 2.0058. Min Range: -2.0058

Max Act: 1.2480. Min Act: -0.0000

Data Index: 960892 (C4 (Web Text))

Max Activating Token Index: 662