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

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

Neuron 4040 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2194. Min Range: -1.2194

Max Act: 1.2194. Min Act: -0.0001

Data Index: 462004 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 1.2194. Min Range: -1.2194

Max Act: 1.1230. Min Act: -0.0001

Data Index: 555688 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 1.2194. Min Range: -1.2194

Max Act: 1.1587. Min Act: -0.0001

Data Index: 856836 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 1.2194. Min Range: -1.2194

Max Act: 1.1150. Min Act: -0.0001

Data Index: 888139 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 1.2194. Min Range: -1.2194

Max Act: 1.0940. Min Act: -0.0001

Data Index: 1041938 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 1.2194. Min Range: -1.2194

Max Act: 1.1379. Min Act: -0.0001

Data Index: 728873 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 1.2194. Min Range: -1.2194

Max Act: 1.1245. Min Act: -0.0001

Data Index: 848780 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 1.2194. Min Range: -1.2194

Max Act: 1.0958. Min Act: -0.0001

Data Index: 983644 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 1.2194. Min Range: -1.2194

Max Act: 1.0963. Min Act: -0.0001

Data Index: 116378 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 1.2194. Min Range: -1.2194

Max Act: 1.0838. Min Act: -0.0001

Data Index: 698795 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 1.2194. Min Range: -1.2194

Max Act: 1.0295. Min Act: -0.0001

Data Index: 1316208 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 1.2194. Min Range: -1.2194

Max Act: 1.0627. Min Act: -0.0001

Data Index: 593425 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 1.2194. Min Range: -1.2194

Max Act: 1.0167. Min Act: -0.0001

Data Index: 749497 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 1.2194. Min Range: -1.2194

Max Act: 1.0252. Min Act: -0.0001

Data Index: 233092 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 1.2194. Min Range: -1.2194

Max Act: 0.9926. Min Act: -0.0001

Data Index: 1183175 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 1.2194. Min Range: -1.2194

Max Act: 0.9848. Min Act: -0.0001

Data Index: 794059 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 1.2194. Min Range: -1.2194

Max Act: 0.9807. Min Act: -0.0001

Data Index: 738341 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 1.2194. Min Range: -1.2194

Max Act: 0.9327. Min Act: -0.0001

Data Index: 1072233 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 1.2194. Min Range: -1.2194

Max Act: 0.9764. Min Act: -0.0001

Data Index: 785947 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 1.2194. Min Range: -1.2194

Max Act: 0.9146. Min Act: -0.0001

Data Index: 724916 (C4 (Web Text))

Max Activating Token Index: 835