Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3274 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.9255. Min Act: -0.0001

Data Index: 14944 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 1.0292. Min Range: -1.0292

Max Act: 1.0292. Min Act: -0.0001

Data Index: 1284460 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.9574. Min Act: -0.0001

Data Index: 208916 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.7999. Min Act: -0.0001

Data Index: 859284 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.8641. Min Act: -0.0001

Data Index: 820069 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.8290. Min Act: -0.0001

Data Index: 205278 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.8522. Min Act: -0.0001

Data Index: 862154 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.9011. Min Act: -0.0001

Data Index: 68864 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.8127. Min Act: -0.0001

Data Index: 279662 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.7784. Min Act: -0.0001

Data Index: 895007 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.7721. Min Act: -0.0001

Data Index: 679646 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.8383. Min Act: -0.0001

Data Index: 506742 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.7536. Min Act: -0.0001

Data Index: 845937 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.7773. Min Act: -0.0001

Data Index: 101248 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.7785. Min Act: -0.0001

Data Index: 433969 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.8217. Min Act: -0.0001

Data Index: 860923 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.7912. Min Act: -0.0001

Data Index: 1011741 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.8148. Min Act: -0.0001

Data Index: 882811 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.7648. Min Act: -0.0001

Data Index: 1187048 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 1.0292. Min Range: -1.0292

Max Act: 0.7367. Min Act: -0.0001

Data Index: 832000 (C4 (Web Text))

Max Activating Token Index: 103