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

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

Neuron 3667 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.5069. Min Act: -0.0001

Data Index: 32293 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.4467. Min Act: -0.0001

Data Index: 1102838 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.4391. Min Act: -0.0001

Data Index: 148862 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.4526. Min Act: -0.0001

Data Index: 835828 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1142492 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.4313. Min Act: -0.0001

Data Index: 170900 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.4124. Min Act: -0.0001

Data Index: 947938 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.4271. Min Act: -0.0001

Data Index: 261791 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.4292. Min Act: -0.0001

Data Index: 741016 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.4217. Min Act: -0.0000

Data Index: 272669 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.3763. Min Act: -0.0000

Data Index: 230128 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.4129. Min Act: -0.0001

Data Index: 143127 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.3991. Min Act: -0.0001

Data Index: 157089 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.3889. Min Act: -0.0001

Data Index: 1030424 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.3998. Min Act: -0.0001

Data Index: 615771 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.4046. Min Act: -0.0001

Data Index: 929184 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.3911. Min Act: -0.0001

Data Index: 985716 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.4068. Min Act: -0.0001

Data Index: 548062 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.3912. Min Act: -0.0001

Data Index: 15671 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.5069. Min Range: -0.5069

Max Act: 0.4024. Min Act: -0.0001

Data Index: 541926 (C4 (Web Text))

Max Activating Token Index: 481