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

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

Neuron 4320 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5190. Min Range: -1.5190

Max Act: 1.5190. Min Act: -0.0000

Data Index: 87935 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 1.5190. Min Range: -1.5190

Max Act: 1.3006. Min Act: -0.0000

Data Index: 189712 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 1.5190. Min Range: -1.5190

Max Act: 1.2694. Min Act: -0.0000

Data Index: 519543 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 1.5190. Min Range: -1.5190

Max Act: 1.2103. Min Act: -0.0000

Data Index: 117187 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 1.5190. Min Range: -1.5190

Max Act: 1.2731. Min Act: -0.0000

Data Index: 434149 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 1.5190. Min Range: -1.5190

Max Act: 1.2315. Min Act: -0.0000

Data Index: 681686 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 1.5190. Min Range: -1.5190

Max Act: 1.1528. Min Act: -0.0000

Data Index: 1025543 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 1.5190. Min Range: -1.5190

Max Act: 1.0899. Min Act: -0.0000

Data Index: 1292721 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 1.5190. Min Range: -1.5190

Max Act: 1.2143. Min Act: -0.0000

Data Index: 594163 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 1.5190. Min Range: -1.5190

Max Act: 1.1265. Min Act: -0.0000

Data Index: 895888 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 1.5190. Min Range: -1.5190

Max Act: 1.1259. Min Act: -0.0000

Data Index: 439657 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 1.5190. Min Range: -1.5190

Max Act: 1.1066. Min Act: -0.0000

Data Index: 224554 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 1.5190. Min Range: -1.5190

Max Act: 1.0082. Min Act: -0.0000

Data Index: 412401 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 1.5190. Min Range: -1.5190

Max Act: 1.1948. Min Act: -0.0000

Data Index: 210362 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 1.5190. Min Range: -1.5190

Max Act: 1.0980. Min Act: -0.0000

Data Index: 1158128 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 1.5190. Min Range: -1.5190

Max Act: 1.0825. Min Act: -0.0000

Data Index: 1093201 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 1.5190. Min Range: -1.5190

Max Act: 1.0252. Min Act: -0.0000

Data Index: 267764 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 1.5190. Min Range: -1.5190

Max Act: 0.9408. Min Act: -0.0000

Data Index: 1540522 (Python Code)

Max Activating Token Index: 572

Text #18

Max Range: 1.5190. Min Range: -1.5190

Max Act: 1.0713. Min Act: -0.0000

Data Index: 535475 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 1.5190. Min Range: -1.5190

Max Act: 1.0729. Min Act: -0.0000

Data Index: 807053 (C4 (Web Text))

Max Activating Token Index: 990