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

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

Neuron 2027 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0145. Min Range: -2.0145

Max Act: 2.0145. Min Act: -0.0000

Data Index: 108858 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 2.0145. Min Range: -2.0145

Max Act: 1.6571. Min Act: -0.0000

Data Index: 866074 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 2.0145. Min Range: -2.0145

Max Act: 1.6979. Min Act: -0.0000

Data Index: 1343158 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 2.0145. Min Range: -2.0145

Max Act: 1.5133. Min Act: -0.0000

Data Index: 6211 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 2.0145. Min Range: -2.0145

Max Act: 1.6196. Min Act: -0.0000

Data Index: 30835 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 2.0145. Min Range: -2.0145

Max Act: 1.5153. Min Act: -0.0000

Data Index: 630190 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 2.0145. Min Range: -2.0145

Max Act: 1.4707. Min Act: -0.0000

Data Index: 702951 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 2.0145. Min Range: -2.0145

Max Act: 1.4423. Min Act: -0.0000

Data Index: 429153 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 2.0145. Min Range: -2.0145

Max Act: 1.4708. Min Act: -0.0000

Data Index: 558484 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 2.0145. Min Range: -2.0145

Max Act: 1.4587. Min Act: -0.0000

Data Index: 262475 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 2.0145. Min Range: -2.0145

Max Act: 1.4557. Min Act: -0.0000

Data Index: 567983 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 2.0145. Min Range: -2.0145

Max Act: 1.4741. Min Act: -0.0000

Data Index: 124669 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 2.0145. Min Range: -2.0145

Max Act: 1.3783. Min Act: -0.0000

Data Index: 575538 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 2.0145. Min Range: -2.0145

Max Act: 1.4778. Min Act: -0.0000

Data Index: 172875 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 2.0145. Min Range: -2.0145

Max Act: 1.3263. Min Act: -0.0000

Data Index: 767693 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 2.0145. Min Range: -2.0145

Max Act: 1.3245. Min Act: -0.0000

Data Index: 268147 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 2.0145. Min Range: -2.0145

Max Act: 1.2893. Min Act: -0.0000

Data Index: 1343507 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 2.0145. Min Range: -2.0145

Max Act: 1.3632. Min Act: -0.0000

Data Index: 131537 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 2.0145. Min Range: -2.0145

Max Act: 1.3077. Min Act: -0.0000

Data Index: 47029 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 2.0145. Min Range: -2.0145

Max Act: 1.2191. Min Act: -0.0000

Data Index: 40555 (C4 (Web Text))

Max Activating Token Index: 251