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

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

Neuron 2048 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: 2.6258. Min Range: -2.6258

Max Act: 2.6258. Min Act: -0.0000

Data Index: 1080855 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 2.6258. Min Range: -2.6258

Max Act: 2.5010. Min Act: -0.0000

Data Index: 1123776 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 2.6258. Min Range: -2.6258

Max Act: 2.4631. Min Act: -0.0000

Data Index: 1054843 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 2.6258. Min Range: -2.6258

Max Act: 2.5734. Min Act: -0.0000

Data Index: 1044060 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 2.6258. Min Range: -2.6258

Max Act: 2.2203. Min Act: -0.0000

Data Index: 1154002 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 2.6258. Min Range: -2.6258

Max Act: 2.2967. Min Act: -0.0000

Data Index: 419487 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 2.6258. Min Range: -2.6258

Max Act: 2.2772. Min Act: -0.0000

Data Index: 1017074 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 2.6258. Min Range: -2.6258

Max Act: 2.1166. Min Act: -0.0000

Data Index: 1138628 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 2.6258. Min Range: -2.6258

Max Act: 2.1567. Min Act: -0.0000

Data Index: 702836 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 2.6258. Min Range: -2.6258

Max Act: 2.1536. Min Act: -0.0000

Data Index: 963395 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 2.6258. Min Range: -2.6258

Max Act: 2.0379. Min Act: -0.0000

Data Index: 804215 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 2.6258. Min Range: -2.6258

Max Act: 2.0316. Min Act: -0.0000

Data Index: 1305920 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 2.6258. Min Range: -2.6258

Max Act: 2.1354. Min Act: -0.0000

Data Index: 894226 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 2.6258. Min Range: -2.6258

Max Act: 2.1052. Min Act: -0.0000

Data Index: 1308332 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 2.6258. Min Range: -2.6258

Max Act: 2.1946. Min Act: -0.0000

Data Index: 152983 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 2.6258. Min Range: -2.6258

Max Act: 2.0504. Min Act: -0.0000

Data Index: 67068 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 2.6258. Min Range: -2.6258

Max Act: 1.9009. Min Act: -0.0000

Data Index: 1080075 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 2.6258. Min Range: -2.6258

Max Act: 1.9871. Min Act: -0.0000

Data Index: 682180 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 2.6258. Min Range: -2.6258

Max Act: 1.8275. Min Act: -0.0000

Data Index: 919168 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 2.6258. Min Range: -2.6258

Max Act: 1.9329. Min Act: -0.0001

Data Index: 392222 (C4 (Web Text))

Max Activating Token Index: 585