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

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

Neuron 4042 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.8366. Min Act: -0.0000

Data Index: 1049311 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1144272 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1222192 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6002. Min Act: -0.0000

Data Index: 255358 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1246793 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6078. Min Act: -0.0000

Data Index: 510968 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6215. Min Act: 0.0000

Data Index: 333101 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.5845. Min Act: -0.0000

Data Index: 472040 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6153. Min Act: 0.0001

Data Index: 563281 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.5660. Min Act: -0.0000

Data Index: 956682 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.5931. Min Act: -0.0000

Data Index: 473706 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1100256 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.6092. Min Act: -0.0000

Data Index: 204115 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.5925. Min Act: -0.0000

Data Index: 129154 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.5498. Min Act: 0.0000

Data Index: 834583 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1288929 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1200937 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.5665. Min Act: -0.0000

Data Index: 453512 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.5275. Min Act: -0.0000

Data Index: 934076 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.8366. Min Range: -0.8366

Max Act: 0.5567. Min Act: -0.0000

Data Index: 1195900 (C4 (Web Text))

Max Activating Token Index: 506