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

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

Neuron 4695 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.6154. Min Act: -0.0000

Data Index: 181888 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.5794. Min Act: -0.0000

Data Index: 306805 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.5467. Min Act: -0.0000

Data Index: 246943 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.5170. Min Act: -0.0000

Data Index: 165760 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.5290. Min Act: -0.0000

Data Index: 1318939 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.5425. Min Act: -0.0000

Data Index: 1137509 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.5397. Min Act: -0.0000

Data Index: 92043 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4896. Min Act: -0.0000

Data Index: 1000265 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4710. Min Act: -0.0000

Data Index: 303041 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4626. Min Act: -0.0000

Data Index: 978600 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4543. Min Act: -0.0000

Data Index: 1348429 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4265. Min Act: -0.0000

Data Index: 126255 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4581. Min Act: -0.0000

Data Index: 792524 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4350. Min Act: -0.0000

Data Index: 716536 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4308. Min Act: -0.0000

Data Index: 37887 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1236788 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4445. Min Act: -0.0000

Data Index: 95935 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4668. Min Act: -0.0000

Data Index: 33710 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4188. Min Act: -0.0000

Data Index: 562338 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4323. Min Act: -0.0000

Data Index: 789920 (C4 (Web Text))

Max Activating Token Index: 317