Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1092 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.2705. Min Act: -0.0005

Data Index: 1159057 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.3271. Min Act: -0.0005

Data Index: 71227 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.2593. Min Act: -0.0005

Data Index: 1279540 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.2852. Min Act: -0.0005

Data Index: 808685 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.2151. Min Act: -0.0005

Data Index: 37147 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.1698. Min Act: -0.0005

Data Index: 226031 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.1493. Min Act: -0.0005

Data Index: 774317 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.2035. Min Act: -0.0005

Data Index: 659508 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.1359. Min Act: -0.0005

Data Index: 958449 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.1045. Min Act: -0.0005

Data Index: 145635 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.1296. Min Act: -0.0005

Data Index: 1082132 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.1080. Min Act: -0.0005

Data Index: 1066908 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.1388. Min Act: -0.0005

Data Index: 1309635 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.1210. Min Act: -0.0005

Data Index: 743670 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.0492. Min Act: -0.0005

Data Index: 248733 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.0813. Min Act: -0.0005

Data Index: 483771 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.0133. Min Act: -0.0005

Data Index: 91576 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.0798. Min Act: -0.0005

Data Index: 1190821 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.0096. Min Act: -0.0005

Data Index: 469001 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.0080. Min Act: -0.0005

Data Index: 541258 (C4 (Web Text))

Max Activating Token Index: 607