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

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

Neuron 5240 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.2087. Min Act: -0.0000

Data Index: 1078394 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.3089. Min Act: -0.0000

Data Index: 665384 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.2804. Min Act: -0.0000

Data Index: 1115973 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.0964. Min Act: -0.0000

Data Index: 1227280 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.2454. Min Act: -0.0000

Data Index: 872658 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.2441. Min Act: -0.0000

Data Index: 1244239 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.1084. Min Act: -0.0000

Data Index: 587195 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.1499. Min Act: -0.0000

Data Index: 922655 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.1459. Min Act: -0.0000

Data Index: 196278 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.1319. Min Act: -0.0000

Data Index: 177906 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.1311. Min Act: -0.0000

Data Index: 152847 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.0673. Min Act: -0.0000

Data Index: 55172 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.1806. Min Act: -0.0000

Data Index: 784873 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.1679. Min Act: -0.0000

Data Index: 276049 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.9744. Min Act: -0.0000

Data Index: 218940 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.1158. Min Act: -0.0000

Data Index: 822288 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.9388. Min Act: -0.0000

Data Index: 192067 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.9322. Min Act: -0.0000

Data Index: 1277261 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.9039. Min Act: -0.0000

Data Index: 332809 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.7749. Min Act: -0.0000

Data Index: 260456 (C4 (Web Text))

Max Activating Token Index: 228