Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1581 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.4637. Min Act: -0.0000

Data Index: 12879 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.4333. Min Act: -0.0000

Data Index: 74974 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.4451. Min Act: -0.0000

Data Index: 894575 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1133032 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.4388. Min Act: -0.0000

Data Index: 545960 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.4395. Min Act: -0.0000

Data Index: 755132 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.4095. Min Act: -0.0000

Data Index: 793818 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1055789 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1230270 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.4320. Min Act: -0.0000

Data Index: 272353 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.4119. Min Act: -0.0000

Data Index: 890688 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.4058. Min Act: -0.0000

Data Index: 1110457 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.4025. Min Act: -0.0000

Data Index: 797757 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.3958. Min Act: -0.0000

Data Index: 421366 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.4051. Min Act: -0.0000

Data Index: 976964 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.3815. Min Act: -0.0000

Data Index: 579619 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1267626 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1107034 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.3855. Min Act: -0.0000

Data Index: 851237 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.4637. Min Range: -0.4637

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1280529 (C4 (Web Text))

Max Activating Token Index: 115