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

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

Neuron 3157 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1421. Min Range: -1.1421

Max Act: 1.1421. Min Act: -0.0000

Data Index: 1151350 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 1.1421. Min Range: -1.1421

Max Act: 1.0059. Min Act: 0.0000

Data Index: 269764 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 1.1421. Min Range: -1.1421

Max Act: 1.0050. Min Act: -0.0000

Data Index: 1002154 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.9439. Min Act: -0.0000

Data Index: 726473 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.7859. Min Act: -0.0000

Data Index: 992295 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.8125. Min Act: -0.0000

Data Index: 858428 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.7667. Min Act: -0.0000

Data Index: 520356 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1347201 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.6987. Min Act: -0.0000

Data Index: 575393 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.6866. Min Act: -0.0000

Data Index: 1119928 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1064932 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.6802. Min Act: -0.0000

Data Index: 560643 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.6498. Min Act: -0.0000

Data Index: 76324 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.6470. Min Act: -0.0000

Data Index: 387062 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.6003. Min Act: -0.0000

Data Index: 1247117 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1031135 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.5954. Min Act: -0.0000

Data Index: 497941 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1240633 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.5643. Min Act: 0.0000

Data Index: 1296337 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.5820. Min Act: -0.0000

Data Index: 624816 (C4 (Web Text))

Max Activating Token Index: 526