Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4197 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0686. Min Range: -1.0686

Max Act: 1.0686. Min Act: -0.0000

Data Index: 479966 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.8351. Min Act: -0.0000

Data Index: 935934 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.8240. Min Act: -0.0000

Data Index: 1277864 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.7904. Min Act: -0.0000

Data Index: 1338191 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.7546. Min Act: -0.0000

Data Index: 958633 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1270528 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.7285. Min Act: -0.0000

Data Index: 161078 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1239689 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.7065. Min Act: -0.0000

Data Index: 639719 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.6939. Min Act: -0.0000

Data Index: 823739 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.6823. Min Act: -0.0000

Data Index: 166059 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.6928. Min Act: -0.0000

Data Index: 320908 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.6967. Min Act: -0.0000

Data Index: 1056610 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.7057. Min Act: -0.0000

Data Index: 580551 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.5725. Min Act: -0.0000

Data Index: 55545 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.6337. Min Act: -0.0000

Data Index: 329771 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.6070. Min Act: -0.0000

Data Index: 676392 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.6663. Min Act: -0.0000

Data Index: 1078034 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.6182. Min Act: -0.0000

Data Index: 1046065 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1008563 (C4 (Web Text))

Max Activating Token Index: 155