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

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

Neuron 4310 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.3410. Min Act: -0.0000

Data Index: 2907 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.2214. Min Act: -0.0000

Data Index: 706473 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.1178. Min Act: -0.0000

Data Index: 777405 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.1373. Min Act: -0.0000

Data Index: 1168375 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.0342. Min Act: -0.0000

Data Index: 778705 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.0290. Min Act: -0.0001

Data Index: 175748 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.0005. Min Act: -0.0000

Data Index: 188839 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1177199 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.9150. Min Act: -0.0000

Data Index: 637828 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.9026. Min Act: -0.0001

Data Index: 705844 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.9079. Min Act: -0.0001

Data Index: 137171 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.8927. Min Act: -0.0000

Data Index: 415782 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.8685. Min Act: -0.0000

Data Index: 1195668 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.8296. Min Act: -0.0000

Data Index: 648546 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.9281. Min Act: -0.0000

Data Index: 356341 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.8505. Min Act: -0.0000

Data Index: 1012824 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1021932 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1110164 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.8106. Min Act: -0.0000

Data Index: 1285451 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.8213. Min Act: -0.0000

Data Index: 1006222 (C4 (Web Text))

Max Activating Token Index: 996