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

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

Neuron 4513 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: 1.0404. Min Range: -1.0404

Max Act: 1.0404. Min Act: -0.0000

Data Index: 771536 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.9282. Min Act: -0.0000

Data Index: 150674 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.9228. Min Act: -0.0000

Data Index: 518665 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.9242. Min Act: -0.0000

Data Index: 765213 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.8858. Min Act: -0.0000

Data Index: 851541 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.8755. Min Act: -0.0000

Data Index: 35383 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.8518. Min Act: -0.0000

Data Index: 356465 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.8521. Min Act: -0.0000

Data Index: 716461 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.8731. Min Act: -0.0000

Data Index: 834646 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.8267. Min Act: -0.0000

Data Index: 561603 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1188099 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.7836. Min Act: -0.0000

Data Index: 156684 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.8113. Min Act: -0.0000

Data Index: 419326 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.8061. Min Act: -0.0000

Data Index: 978538 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.7913. Min Act: -0.0000

Data Index: 416150 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1170723 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.7404. Min Act: -0.0000

Data Index: 1351576 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.7732. Min Act: -0.0000

Data Index: 243918 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.7784. Min Act: -0.0000

Data Index: 432534 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 1.0404. Min Range: -1.0404

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1306196 (C4 (Web Text))

Max Activating Token Index: 729