Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2178 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.9151. Min Act: -0.0002

Data Index: 1359166 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.9284. Min Act: -0.0002

Data Index: 446252 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.8028. Min Act: -0.0001

Data Index: 1327057 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.7400. Min Act: -0.0001

Data Index: 169093 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.7740. Min Act: -0.0001

Data Index: 278726 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.7510. Min Act: -0.0002

Data Index: 1183135 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6469. Min Act: -0.0002

Data Index: 750470 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.8216. Min Act: -0.0001

Data Index: 1102722 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.7335. Min Act: -0.0002

Data Index: 631693 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6550. Min Act: -0.0002

Data Index: 328059 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.7417. Min Act: -0.0001

Data Index: 1073373 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6394. Min Act: -0.0002

Data Index: 1014432 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6300. Min Act: -0.0001

Data Index: 275451 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6695. Min Act: -0.0002

Data Index: 506648 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6687. Min Act: -0.0001

Data Index: 1290758 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6544. Min Act: -0.0001

Data Index: 1175919 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6015. Min Act: -0.0002

Data Index: 737677 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6983. Min Act: -0.0001

Data Index: 541067 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6817. Min Act: -0.0001

Data Index: 377568 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6879. Min Act: -0.0001

Data Index: 744578 (C4 (Web Text))

Max Activating Token Index: 41