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

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

Neuron 3049 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1435. Min Range: -1.1435

Max Act: 1.1435. Min Act: -0.0000

Data Index: 826555 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 1.1435. Min Range: -1.1435

Max Act: 1.0157. Min Act: -0.0000

Data Index: 435881 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 1.1435. Min Range: -1.1435

Max Act: 1.0368. Min Act: -0.0000

Data Index: 502246 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.8702. Min Act: -0.0000

Data Index: 917661 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.9133. Min Act: -0.0000

Data Index: 44222 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.8931. Min Act: -0.0000

Data Index: 219450 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.8435. Min Act: -0.0000

Data Index: 519133 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.8744. Min Act: -0.0000

Data Index: 876007 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.8540. Min Act: -0.0000

Data Index: 863645 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.8800. Min Act: -0.0000

Data Index: 1348582 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.8399. Min Act: -0.0000

Data Index: 1339164 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.8691. Min Act: -0.0000

Data Index: 476107 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.8209. Min Act: -0.0000

Data Index: 414754 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.8101. Min Act: -0.0000

Data Index: 1345217 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.8484. Min Act: -0.0000

Data Index: 644236 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.8866. Min Act: -0.0000

Data Index: 589845 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.8053. Min Act: -0.0000

Data Index: 435902 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.8212. Min Act: -0.0000

Data Index: 898226 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.7672. Min Act: -0.0000

Data Index: 215818 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 1.1435. Min Range: -1.1435

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1315 (C4 (Web Text))

Max Activating Token Index: 279