Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2526 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9514. Min Range: -2.9514

Max Act: 2.9514. Min Act: -0.0000

Data Index: 1236794 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 2.9514. Min Range: -2.9514

Max Act: 2.3132. Min Act: -0.0000

Data Index: 912196 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 2.9514. Min Range: -2.9514

Max Act: 2.2384. Min Act: -0.0000

Data Index: 195470 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 2.9514. Min Range: -2.9514

Max Act: 2.1565. Min Act: -0.0000

Data Index: 468353 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 2.9514. Min Range: -2.9514

Max Act: 2.0129. Min Act: -0.0000

Data Index: 154034 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 2.9514. Min Range: -2.9514

Max Act: 2.1236. Min Act: -0.0000

Data Index: 1220565 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 2.9514. Min Range: -2.9514

Max Act: 2.1233. Min Act: -0.0000

Data Index: 1159997 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 2.9514. Min Range: -2.9514

Max Act: 2.1336. Min Act: -0.0000

Data Index: 375106 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 2.9514. Min Range: -2.9514

Max Act: 2.1128. Min Act: -0.0000

Data Index: 899770 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 2.9514. Min Range: -2.9514

Max Act: 2.0579. Min Act: -0.0000

Data Index: 419044 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 2.9514. Min Range: -2.9514

Max Act: 2.0829. Min Act: -0.0000

Data Index: 572563 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 2.9514. Min Range: -2.9514

Max Act: 1.9558. Min Act: -0.0000

Data Index: 747975 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 2.9514. Min Range: -2.9514

Max Act: 2.0304. Min Act: -0.0000

Data Index: 1095313 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 2.9514. Min Range: -2.9514

Max Act: 2.0506. Min Act: -0.0000

Data Index: 137929 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 2.9514. Min Range: -2.9514

Max Act: 1.9171. Min Act: -0.0000

Data Index: 571186 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 2.9514. Min Range: -2.9514

Max Act: 2.0090. Min Act: -0.0000

Data Index: 984735 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 2.9514. Min Range: -2.9514

Max Act: 1.8898. Min Act: -0.0000

Data Index: 82608 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 2.9514. Min Range: -2.9514

Max Act: 2.0000. Min Act: -0.0000

Data Index: 114348 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 2.9514. Min Range: -2.9514

Max Act: 1.8841. Min Act: -0.0000

Data Index: 198810 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 2.9514. Min Range: -2.9514

Max Act: 1.9596. Min Act: -0.0000

Data Index: 233225 (C4 (Web Text))

Max Activating Token Index: 349