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

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

Neuron 5496 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1330. Min Range: -1.1330

Max Act: 1.0987. Min Act: -0.0001

Data Index: 419257 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 1.1330. Min Range: -1.1330

Max Act: 1.0761. Min Act: -0.0001

Data Index: 501990 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 1.1330. Min Range: -1.1330

Max Act: 1.1330. Min Act: -0.0001

Data Index: 1197600 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.9810. Min Act: -0.0001

Data Index: 659996 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.9768. Min Act: -0.0001

Data Index: 1339196 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 1.1330. Min Range: -1.1330

Max Act: 1.0043. Min Act: -0.0001

Data Index: 374531 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.9946. Min Act: -0.0001

Data Index: 338150 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 1.1330. Min Range: -1.1330

Max Act: 1.0217. Min Act: -0.0001

Data Index: 702919 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.9668. Min Act: -0.0001

Data Index: 456205 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.9584. Min Act: -0.0001

Data Index: 624952 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 1.1330. Min Range: -1.1330

Max Act: 1.0089. Min Act: -0.0001

Data Index: 190736 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.9684. Min Act: -0.0001

Data Index: 614777 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.8577. Min Act: -0.0001

Data Index: 1154508 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.9092. Min Act: -0.0001

Data Index: 217037 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.8082. Min Act: -0.0001

Data Index: 1187471 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.9174. Min Act: -0.0001

Data Index: 1066301 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.8338. Min Act: -0.0001

Data Index: 744909 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.8903. Min Act: -0.0001

Data Index: 1229270 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.8421. Min Act: -0.0001

Data Index: 212803 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 1.1330. Min Range: -1.1330

Max Act: 0.8783. Min Act: -0.0001

Data Index: 1165525 (C4 (Web Text))

Max Activating Token Index: 427