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

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

Neuron 676 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5643. Min Act: -0.0001

Data Index: 1177278 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.6037. Min Act: -0.0001

Data Index: 990187 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5931. Min Act: -0.0001

Data Index: 1091389 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.6064. Min Act: -0.0001

Data Index: 459919 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5418. Min Act: -0.0001

Data Index: 692052 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5015. Min Act: -0.0001

Data Index: 27118 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5412. Min Act: -0.0001

Data Index: 493556 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4773. Min Act: -0.0001

Data Index: 973481 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4593. Min Act: -0.0001

Data Index: 797132 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5332. Min Act: -0.0001

Data Index: 657700 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5091. Min Act: -0.0001

Data Index: 786592 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4436. Min Act: -0.0001

Data Index: 434604 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5226. Min Act: -0.0001

Data Index: 733032 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4098. Min Act: -0.0001

Data Index: 1018186 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4290. Min Act: -0.0001

Data Index: 772610 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4152. Min Act: -0.0001

Data Index: 164095 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4373. Min Act: -0.0001

Data Index: 1138534 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4236. Min Act: -0.0001

Data Index: 1012492 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4260. Min Act: -0.0001

Data Index: 571867 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4351. Min Act: -0.0001

Data Index: 354808 (C4 (Web Text))

Max Activating Token Index: 290