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

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

Neuron 4545 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2248. Min Range: -2.2248

Max Act: 2.2248. Min Act: -0.0000

Data Index: 662123 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 2.2248. Min Range: -2.2248

Max Act: 1.8224. Min Act: -0.0000

Data Index: 537836 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 2.2248. Min Range: -2.2248

Max Act: 1.8561. Min Act: -0.0000

Data Index: 807887 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 2.2248. Min Range: -2.2248

Max Act: 1.5929. Min Act: -0.0000

Data Index: 308129 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 2.2248. Min Range: -2.2248

Max Act: 1.4646. Min Act: -0.0000

Data Index: 378412 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 2.2248. Min Range: -2.2248

Max Act: 1.2532. Min Act: -0.0000

Data Index: 647348 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 2.2248. Min Range: -2.2248

Max Act: 1.0044. Min Act: -0.0000

Data Index: 195656 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 2.2248. Min Range: -2.2248

Max Act: 0.9574. Min Act: -0.0000

Data Index: 52217 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 2.2248. Min Range: -2.2248

Max Act: 0.8304. Min Act: -0.0000

Data Index: 803279 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 2.2248. Min Range: -2.2248

Max Act: 0.9107. Min Act: -0.0000

Data Index: 752001 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 2.2248. Min Range: -2.2248

Max Act: 0.9134. Min Act: -0.0000

Data Index: 1343858 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 2.2248. Min Range: -2.2248

Max Act: 0.8475. Min Act: -0.0000

Data Index: 1324380 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 2.2248. Min Range: -2.2248

Max Act: 0.8480. Min Act: -0.0000

Data Index: 588609 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 2.2248. Min Range: -2.2248

Max Act: 0.8178. Min Act: -0.0000

Data Index: 223896 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 2.2248. Min Range: -2.2248

Max Act: 0.8807. Min Act: 0.0000

Data Index: 459211 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 2.2248. Min Range: -2.2248

Max Act: 0.8839. Min Act: -0.0000

Data Index: 122409 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 2.2248. Min Range: -2.2248

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1202949 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 2.2248. Min Range: -2.2248

Max Act: 0.8134. Min Act: -0.0000

Data Index: 994121 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 2.2248. Min Range: -2.2248

Max Act: 0.6904. Min Act: -0.0000

Data Index: 842765 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 2.2248. Min Range: -2.2248

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1276057 (C4 (Web Text))

Max Activating Token Index: 94