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

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

Neuron 2781 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1058. Min Range: -6.1058

Max Act: 6.1058. Min Act: -0.0000

Data Index: 180742 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 6.1058. Min Range: -6.1058

Max Act: 5.6207. Min Act: -0.0000

Data Index: 675188 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 6.1058. Min Range: -6.1058

Max Act: 5.3751. Min Act: -0.0000

Data Index: 442811 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 6.1058. Min Range: -6.1058

Max Act: 4.7546. Min Act: -0.0000

Data Index: 1294305 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 6.1058. Min Range: -6.1058

Max Act: 5.1078. Min Act: -0.0000

Data Index: 719096 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 6.1058. Min Range: -6.1058

Max Act: 5.2131. Min Act: -0.0001

Data Index: 384756 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 6.1058. Min Range: -6.1058

Max Act: 4.9518. Min Act: -0.0000

Data Index: 563638 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 6.1058. Min Range: -6.1058

Max Act: 5.2314. Min Act: -0.0000

Data Index: 349718 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 6.1058. Min Range: -6.1058

Max Act: 4.7617. Min Act: -0.0001

Data Index: 954481 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 6.1058. Min Range: -6.1058

Max Act: 4.5504. Min Act: -0.0000

Data Index: 943568 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 6.1058. Min Range: -6.1058

Max Act: 4.6810. Min Act: -0.0000

Data Index: 493778 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 6.1058. Min Range: -6.1058

Max Act: 4.4654. Min Act: -0.0000

Data Index: 646129 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 6.1058. Min Range: -6.1058

Max Act: 4.2479. Min Act: -0.0000

Data Index: 64726 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 6.1058. Min Range: -6.1058

Max Act: 4.6321. Min Act: -0.0000

Data Index: 979423 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 6.1058. Min Range: -6.1058

Max Act: 4.3815. Min Act: -0.0000

Data Index: 721563 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 6.1058. Min Range: -6.1058

Max Act: 4.3544. Min Act: -0.0000

Data Index: 1026057 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 6.1058. Min Range: -6.1058

Max Act: 4.3675. Min Act: -0.0001

Data Index: 712421 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 6.1058. Min Range: -6.1058

Max Act: 4.0103. Min Act: -0.0000

Data Index: 1253629 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 6.1058. Min Range: -6.1058

Max Act: 4.3130. Min Act: -0.0000

Data Index: 657752 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 6.1058. Min Range: -6.1058

Max Act: 4.3240. Min Act: -0.0000

Data Index: 340643 (C4 (Web Text))

Max Activating Token Index: 271