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

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

Neuron 2918 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: 2.9510. Min Range: -2.9510

Max Act: 2.9510. Min Act: -0.0000

Data Index: 521453 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 2.9510. Min Range: -2.9510

Max Act: 2.8940. Min Act: -0.0000

Data Index: 1071470 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 2.9510. Min Range: -2.9510

Max Act: 2.9193. Min Act: -0.0000

Data Index: 1046191 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 2.9510. Min Range: -2.9510

Max Act: 2.6705. Min Act: -0.0000

Data Index: 466037 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 2.9510. Min Range: -2.9510

Max Act: 2.5937. Min Act: -0.0000

Data Index: 406836 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 2.9510. Min Range: -2.9510

Max Act: 2.5836. Min Act: -0.0000

Data Index: 506354 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 2.9510. Min Range: -2.9510

Max Act: 2.3774. Min Act: -0.0000

Data Index: 543576 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 2.9510. Min Range: -2.9510

Max Act: 2.3450. Min Act: -0.0000

Data Index: 419172 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 2.9510. Min Range: -2.9510

Max Act: 2.4180. Min Act: -0.0000

Data Index: 1167934 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 2.9510. Min Range: -2.9510

Max Act: 2.3644. Min Act: -0.0000

Data Index: 1086279 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 2.9510. Min Range: -2.9510

Max Act: 2.1870. Min Act: -0.0000

Data Index: 1002206 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 2.9510. Min Range: -2.9510

Max Act: 2.2863. Min Act: -0.0000

Data Index: 1124566 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 2.9510. Min Range: -2.9510

Max Act: 2.2843. Min Act: -0.0000

Data Index: 733546 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 2.9510. Min Range: -2.9510

Max Act: 2.1315. Min Act: -0.0000

Data Index: 823636 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 2.9510. Min Range: -2.9510

Max Act: 2.2569. Min Act: -0.0000

Data Index: 631788 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 2.9510. Min Range: -2.9510

Max Act: 2.2355. Min Act: -0.0000

Data Index: 114614 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 2.9510. Min Range: -2.9510

Max Act: 2.2133. Min Act: -0.0000

Data Index: 814175 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 2.9510. Min Range: -2.9510

Max Act: 2.3416. Min Act: -0.0000

Data Index: 1145792 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 2.9510. Min Range: -2.9510

Max Act: 2.2245. Min Act: -0.0000

Data Index: 201487 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 2.9510. Min Range: -2.9510

Max Act: 2.2247. Min Act: -0.0000

Data Index: 95631 (C4 (Web Text))

Max Activating Token Index: 425