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

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

Neuron 2728 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: 1.5032. Min Range: -1.5032

Max Act: 1.5032. Min Act: -0.0000

Data Index: 81110 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 1.5032. Min Range: -1.5032

Max Act: 1.2489. Min Act: -0.0001

Data Index: 763424 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 1.5032. Min Range: -1.5032

Max Act: 1.1474. Min Act: -0.0000

Data Index: 46138 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 1.5032. Min Range: -1.5032

Max Act: 1.1234. Min Act: -0.0000

Data Index: 309140 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 1.5032. Min Range: -1.5032

Max Act: 1.1188. Min Act: -0.0000

Data Index: 1181052 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 1.5032. Min Range: -1.5032

Max Act: 1.1574. Min Act: -0.0000

Data Index: 124688 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 1.5032. Min Range: -1.5032

Max Act: 1.0561. Min Act: -0.0001

Data Index: 561413 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 1.5032. Min Range: -1.5032

Max Act: 1.0427. Min Act: -0.0000

Data Index: 887706 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 1.5032. Min Range: -1.5032

Max Act: 1.0209. Min Act: -0.0000

Data Index: 877428 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 1.5032. Min Range: -1.5032

Max Act: 0.9796. Min Act: -0.0000

Data Index: 168086 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 1.5032. Min Range: -1.5032

Max Act: 0.8836. Min Act: -0.0000

Data Index: 131252 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 1.5032. Min Range: -1.5032

Max Act: 0.9056. Min Act: -0.0000

Data Index: 745689 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 1.5032. Min Range: -1.5032

Max Act: 0.8541. Min Act: -0.0000

Data Index: 750165 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 1.5032. Min Range: -1.5032

Max Act: 0.7485. Min Act: -0.0000

Data Index: 158108 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 1.5032. Min Range: -1.5032

Max Act: 0.7946. Min Act: -0.0000

Data Index: 855986 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 1.5032. Min Range: -1.5032

Max Act: 0.8299. Min Act: -0.0000

Data Index: 599891 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 1.5032. Min Range: -1.5032

Max Act: 0.8037. Min Act: -0.0000

Data Index: 681526 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 1.5032. Min Range: -1.5032

Max Act: 0.7897. Min Act: -0.0000

Data Index: 269749 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 1.5032. Min Range: -1.5032

Max Act: 0.8502. Min Act: -0.0000

Data Index: 425064 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 1.5032. Min Range: -1.5032

Max Act: 0.7678. Min Act: -0.0000

Data Index: 1002819 (C4 (Web Text))

Max Activating Token Index: 132