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

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

Neuron 2711 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0657. Min Range: -2.0657

Max Act: 2.0024. Min Act: -0.0000

Data Index: 1041147 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 2.0657. Min Range: -2.0657

Max Act: 2.0657. Min Act: -0.0000

Data Index: 648669 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 2.0657. Min Range: -2.0657

Max Act: 1.8509. Min Act: -0.0000

Data Index: 1553815 (Python Code)

Max Activating Token Index: 965

Text #3

Max Range: 2.0657. Min Range: -2.0657

Max Act: 1.7871. Min Act: -0.0000

Data Index: 1319004 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 2.0657. Min Range: -2.0657

Max Act: 1.4485. Min Act: -0.0000

Data Index: 997310 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 2.0657. Min Range: -2.0657

Max Act: 1.5817. Min Act: -0.0000

Data Index: 1291807 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 2.0657. Min Range: -2.0657

Max Act: 1.5066. Min Act: -0.0000

Data Index: 808933 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 2.0657. Min Range: -2.0657

Max Act: 1.3360. Min Act: -0.0000

Data Index: 425730 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 2.0657. Min Range: -2.0657

Max Act: 1.3009. Min Act: -0.0000

Data Index: 1530706 (Python Code)

Max Activating Token Index: 811

Text #9

Max Range: 2.0657. Min Range: -2.0657

Max Act: 1.2016. Min Act: -0.0000

Data Index: 538038 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 2.0657. Min Range: -2.0657

Max Act: 1.2923. Min Act: -0.0000

Data Index: 880683 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 2.0657. Min Range: -2.0657

Max Act: 1.2918. Min Act: -0.0000

Data Index: 875247 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 2.0657. Min Range: -2.0657

Max Act: 1.3694. Min Act: -0.0000

Data Index: 235818 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 2.0657. Min Range: -2.0657

Max Act: 1.3243. Min Act: -0.0000

Data Index: 1039381 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 2.0657. Min Range: -2.0657

Max Act: 1.0070. Min Act: -0.0000

Data Index: 171115 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 2.0657. Min Range: -2.0657

Max Act: 1.2200. Min Act: -0.0000

Data Index: 986943 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 2.0657. Min Range: -2.0657

Max Act: 1.0267. Min Act: -0.0000

Data Index: 941121 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 2.0657. Min Range: -2.0657

Max Act: 1.0191. Min Act: -0.0000

Data Index: 1388372 (Python Code)

Max Activating Token Index: 830

Text #18

Max Range: 2.0657. Min Range: -2.0657

Max Act: 1.2886. Min Act: -0.0000

Data Index: 1294413 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 2.0657. Min Range: -2.0657

Max Act: 1.0319. Min Act: -0.0000

Data Index: 1199472 (C4 (Web Text))

Max Activating Token Index: 43