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

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

Neuron 3182 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.3573. Min Act: -0.0001

Data Index: 347887 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.2688. Min Act: -0.0001

Data Index: 960774 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.2811. Min Act: -0.0001

Data Index: 1338118 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.3015. Min Act: -0.0001

Data Index: 764823 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.3067. Min Act: -0.0001

Data Index: 744025 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.2068. Min Act: -0.0001

Data Index: 731782 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.2347. Min Act: -0.0001

Data Index: 36278 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.1811. Min Act: -0.0001

Data Index: 345544 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.1403. Min Act: -0.0001

Data Index: 333002 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.2357. Min Act: -0.0001

Data Index: 1207493 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.1184. Min Act: -0.0001

Data Index: 1094336 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.0917. Min Act: -0.0001

Data Index: 942494 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.0045. Min Act: -0.0001

Data Index: 198271 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.1325. Min Act: -0.0001

Data Index: 1351155 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.1650. Min Act: -0.0001

Data Index: 824871 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.0864. Min Act: -0.0001

Data Index: 863094 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.1201. Min Act: -0.0001

Data Index: 1278332 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.1623. Min Act: -0.0001

Data Index: 1013734 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.0468. Min Act: -0.0001

Data Index: 254668 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 1.3573. Min Range: -1.3573

Max Act: 1.1438. Min Act: -0.0001

Data Index: 1111248 (C4 (Web Text))

Max Activating Token Index: 423