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

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

Neuron 1422 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.2523. Min Act: -0.0000

Data Index: 110308 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.1780. Min Act: -0.0000

Data Index: 1500971 (Python Code)

Max Activating Token Index: 64

Text #2

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.2002. Min Act: -0.0000

Data Index: 778272 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.2389. Min Act: -0.0000

Data Index: 78644 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.1209. Min Act: -0.0000

Data Index: 1321075 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.1139. Min Act: -0.0000

Data Index: 4079 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.2085. Min Act: -0.0000

Data Index: 448179 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.0750. Min Act: -0.0000

Data Index: 1172384 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.1579. Min Act: -0.0000

Data Index: 197870 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.0579. Min Act: -0.0000

Data Index: 915622 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.0991. Min Act: -0.0000

Data Index: 150548 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.0846. Min Act: -0.0000

Data Index: 139164 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.0523. Min Act: -0.0000

Data Index: 818416 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.0963. Min Act: -0.0000

Data Index: 1213910 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.0122. Min Act: -0.0000

Data Index: 764072 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.0054. Min Act: -0.0000

Data Index: 1215339 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.0609. Min Act: -0.0000

Data Index: 493979 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.0373. Min Act: -0.0000

Data Index: 119638 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 1.2523. Min Range: -1.2523

Max Act: 1.0587. Min Act: -0.0000

Data Index: 321699 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 1.2523. Min Range: -1.2523

Max Act: 0.9415. Min Act: -0.0000

Data Index: 519820 (C4 (Web Text))

Max Activating Token Index: 742