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

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

Neuron 4114 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.6058. Min Act: -0.0000

Data Index: 618014 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5560. Min Act: -0.0000

Data Index: 796593 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5079. Min Act: -0.0000

Data Index: 26779 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4875. Min Act: -0.0000

Data Index: 202056 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4879. Min Act: -0.0000

Data Index: 176449 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1228328 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4872. Min Act: -0.0000

Data Index: 328914 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4493. Min Act: -0.0000

Data Index: 338410 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4586. Min Act: -0.0000

Data Index: 1179523 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4308. Min Act: -0.0000

Data Index: 366900 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1307726 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.3990. Min Act: -0.0000

Data Index: 1113865 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1185150 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4380. Min Act: -0.0000

Data Index: 1284272 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4305. Min Act: -0.0000

Data Index: 900267 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4021. Min Act: -0.0000

Data Index: 172413 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1400491 (Python Code)

Max Activating Token Index: 361

Text #17

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4145. Min Act: -0.0000

Data Index: 439659 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.3844. Min Act: -0.0000

Data Index: 271682 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4035. Min Act: -0.0000

Data Index: 355742 (C4 (Web Text))

Max Activating Token Index: 29