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

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

Neuron 3700 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1380. Min Range: -5.1380

Max Act: 5.1380. Min Act: -0.0000

Data Index: 752591 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 5.1380. Min Range: -5.1380

Max Act: 4.5004. Min Act: -0.0000

Data Index: 1242536 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 5.1380. Min Range: -5.1380

Max Act: 4.3485. Min Act: -0.0000

Data Index: 310625 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 5.1380. Min Range: -5.1380

Max Act: 4.5394. Min Act: -0.0000

Data Index: 731576 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 5.1380. Min Range: -5.1380

Max Act: 4.1502. Min Act: -0.0000

Data Index: 1081672 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 5.1380. Min Range: -5.1380

Max Act: 4.4839. Min Act: -0.0000

Data Index: 283551 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 5.1380. Min Range: -5.1380

Max Act: 4.4157. Min Act: -0.0000

Data Index: 181658 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 5.1380. Min Range: -5.1380

Max Act: 4.5857. Min Act: -0.0000

Data Index: 494399 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 5.1380. Min Range: -5.1380

Max Act: 3.9957. Min Act: -0.0000

Data Index: 453068 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 5.1380. Min Range: -5.1380

Max Act: 4.0631. Min Act: -0.0000

Data Index: 318048 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 5.1380. Min Range: -5.1380

Max Act: 4.1040. Min Act: -0.0000

Data Index: 850134 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 5.1380. Min Range: -5.1380

Max Act: 4.2339. Min Act: -0.0000

Data Index: 446461 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 5.1380. Min Range: -5.1380

Max Act: 4.1674. Min Act: -0.0000

Data Index: 776542 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 5.1380. Min Range: -5.1380

Max Act: 4.1758. Min Act: -0.0000

Data Index: 998910 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 5.1380. Min Range: -5.1380

Max Act: 4.2324. Min Act: -0.0000

Data Index: 773247 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 5.1380. Min Range: -5.1380

Max Act: 3.8976. Min Act: -0.0000

Data Index: 866505 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 5.1380. Min Range: -5.1380

Max Act: 3.9080. Min Act: -0.0000

Data Index: 179022 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 5.1380. Min Range: -5.1380

Max Act: 3.8818. Min Act: -0.0000

Data Index: 1278528 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 5.1380. Min Range: -5.1380

Max Act: 4.0554. Min Act: -0.0000

Data Index: 10810 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 5.1380. Min Range: -5.1380

Max Act: 3.8512. Min Act: -0.0000

Data Index: 803612 (C4 (Web Text))

Max Activating Token Index: 87