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

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

Neuron 1906 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.9516. Min Act: -0.0001

Data Index: 1086403 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.8746. Min Act: -0.0001

Data Index: 483870 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.8000. Min Act: -0.0001

Data Index: 768601 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.7575. Min Act: -0.0001

Data Index: 1145598 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.7262. Min Act: -0.0000

Data Index: 626965 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.7171. Min Act: -0.0001

Data Index: 972851 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6613. Min Act: -0.0001

Data Index: 996200 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.7276. Min Act: -0.0001

Data Index: 1340321 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6736. Min Act: -0.0001

Data Index: 1058578 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.7267. Min Act: -0.0001

Data Index: 569113 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.7100. Min Act: -0.0001

Data Index: 100352 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.7082. Min Act: -0.0001

Data Index: 371572 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.7097. Min Act: -0.0001

Data Index: 138237 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6794. Min Act: -0.0001

Data Index: 344339 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6566. Min Act: -0.0001

Data Index: 1334055 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6999. Min Act: -0.0001

Data Index: 1320714 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6688. Min Act: -0.0001

Data Index: 764706 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6422. Min Act: -0.0001

Data Index: 605919 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6140. Min Act: -0.0001

Data Index: 562070 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6330. Min Act: -0.0001

Data Index: 941805 (C4 (Web Text))

Max Activating Token Index: 452