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

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

Neuron 1480 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.4122. Min Act: -0.0000

Data Index: 475461 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.3359. Min Act: -0.0000

Data Index: 511771 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.3147. Min Act: -0.0000

Data Index: 512671 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.3215. Min Act: -0.0000

Data Index: 1292425 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.3172. Min Act: 0.0000

Data Index: 151902 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.3049. Min Act: -0.0000

Data Index: 800365 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.3064. Min Act: -0.0000

Data Index: 814973 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.3059. Min Act: -0.0000

Data Index: 927053 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1322457 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.2729. Min Act: -0.0000

Data Index: 506999 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.2806. Min Act: -0.0000

Data Index: 88017 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.2733. Min Act: -0.0000

Data Index: 347973 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.2716. Min Act: -0.0000

Data Index: 460187 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.2698. Min Act: -0.0000

Data Index: 441986 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.2768. Min Act: -0.0000

Data Index: 848647 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.2598. Min Act: -0.0000

Data Index: 984129 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.2627. Min Act: -0.0000

Data Index: 299545 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.2692. Min Act: -0.0000

Data Index: 432588 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.2575. Min Act: -0.0000

Data Index: 1123494 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.4122. Min Range: -0.4122

Max Act: 0.2482. Min Act: 0.0000

Data Index: 122415 (C4 (Web Text))

Max Activating Token Index: 61