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

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

Neuron 3684 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1480. Min Range: -1.1480

Max Act: 1.1480. Min Act: -0.0001

Data Index: 313835 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 1.1480. Min Range: -1.1480

Max Act: 1.1320. Min Act: -0.0001

Data Index: 1206744 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 1.1480. Min Range: -1.1480

Max Act: 1.1291. Min Act: -0.0001

Data Index: 1014420 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 1.1480. Min Range: -1.1480

Max Act: 1.0511. Min Act: -0.0001

Data Index: 1171440 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.9647. Min Act: -0.0001

Data Index: 706874 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.9458. Min Act: -0.0001

Data Index: 680209 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.9014. Min Act: -0.0001

Data Index: 322280 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.8166. Min Act: -0.0001

Data Index: 713598 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.7485. Min Act: -0.0001

Data Index: 658400 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.7527. Min Act: -0.0001

Data Index: 968931 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.7053. Min Act: -0.0001

Data Index: 1203831 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.6758. Min Act: -0.0001

Data Index: 593067 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.6180. Min Act: -0.0001

Data Index: 523940 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.6973. Min Act: -0.0001

Data Index: 1170704 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.6727. Min Act: -0.0001

Data Index: 1176483 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.6665. Min Act: -0.0001

Data Index: 268769 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.7295. Min Act: -0.0001

Data Index: 532611 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.6381. Min Act: -0.0001

Data Index: 1122095 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.6762. Min Act: -0.0001

Data Index: 1334322 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.6097. Min Act: -0.0001

Data Index: 757204 (C4 (Web Text))

Max Activating Token Index: 764