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

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

Neuron 3544 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.1937. Min Act: -0.0002

Data Index: 887181 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.1883. Min Act: -0.0002

Data Index: 304030 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.1613. Min Act: -0.0002

Data Index: 297436 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0851. Min Act: -0.0002

Data Index: 1253506 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0753. Min Act: -0.0002

Data Index: 881519 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0304. Min Act: -0.0002

Data Index: 309937 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0503. Min Act: -0.0002

Data Index: 1242209 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0760. Min Act: -0.0002

Data Index: 778895 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 1.1937. Min Range: -1.1937

Max Act: 0.9487. Min Act: -0.0002

Data Index: 1341694 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 1.1937. Min Range: -1.1937

Max Act: 1.0040. Min Act: -0.0002

Data Index: 1056559 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 1.1937. Min Range: -1.1937

Max Act: 0.9996. Min Act: -0.0002

Data Index: 403943 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 1.1937. Min Range: -1.1937

Max Act: 0.9491. Min Act: -0.0002

Data Index: 597054 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 1.1937. Min Range: -1.1937

Max Act: 0.9696. Min Act: -0.0002

Data Index: 1057139 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 1.1937. Min Range: -1.1937

Max Act: 0.9444. Min Act: -0.0002

Data Index: 199881 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 1.1937. Min Range: -1.1937

Max Act: 0.9356. Min Act: -0.0002

Data Index: 834972 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 1.1937. Min Range: -1.1937

Max Act: 0.9252. Min Act: -0.0002

Data Index: 393634 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 1.1937. Min Range: -1.1937

Max Act: 0.9285. Min Act: -0.0002

Data Index: 653682 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 1.1937. Min Range: -1.1937

Max Act: 0.9243. Min Act: -0.0002

Data Index: 866199 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 1.1937. Min Range: -1.1937

Max Act: 0.9165. Min Act: -0.0002

Data Index: 1215841 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 1.1937. Min Range: -1.1937

Max Act: 0.9111. Min Act: -0.0002

Data Index: 428532 (C4 (Web Text))

Max Activating Token Index: 354