Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2264 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.5131. Min Act: -0.0001

Data Index: 941332 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.5247. Min Act: -0.0001

Data Index: 991126 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4446. Min Act: -0.0001

Data Index: 1246366 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4761. Min Act: -0.0001

Data Index: 478851 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4344. Min Act: -0.0001

Data Index: 1003672 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.3896. Min Act: -0.0001

Data Index: 1066425 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.3901. Min Act: -0.0001

Data Index: 646699 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.4017. Min Act: -0.0001

Data Index: 1093417 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.3862. Min Act: -0.0001

Data Index: 1283989 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.3815. Min Act: -0.0001

Data Index: 1157388 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.3453. Min Act: -0.0001

Data Index: 312680 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.3251. Min Act: -0.0001

Data Index: 930753 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.3545. Min Act: -0.0001

Data Index: 177036 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.3323. Min Act: -0.0001

Data Index: 848412 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.3252. Min Act: -0.0001

Data Index: 356964 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.3237. Min Act: -0.0001

Data Index: 842894 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.3335. Min Act: -0.0001

Data Index: 966775 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.3376. Min Act: -0.0001

Data Index: 1045614 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.3263. Min Act: -0.0001

Data Index: 311825 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 0.5247. Min Range: -0.5247

Max Act: 0.3198. Min Act: -0.0001

Data Index: 316017 (C4 (Web Text))

Max Activating Token Index: 810