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

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

Neuron 5035 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1798. Min Range: -1.1798

Max Act: 1.1798. Min Act: -0.0002

Data Index: 1120072 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.9869. Min Act: -0.0002

Data Index: 1046179 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.8902. Min Act: -0.0002

Data Index: 324398 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.9634. Min Act: -0.0002

Data Index: 159088 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.8929. Min Act: -0.0002

Data Index: 478804 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.8869. Min Act: -0.0002

Data Index: 1146625 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 1.1798. Min Range: -1.1798

Max Act: 1.0446. Min Act: -0.0002

Data Index: 155435 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.9335. Min Act: -0.0002

Data Index: 1268236 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.7965. Min Act: -0.0002

Data Index: 990211 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.8012. Min Act: -0.0002

Data Index: 1114366 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.9660. Min Act: -0.0002

Data Index: 538043 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.8569. Min Act: -0.0002

Data Index: 733389 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.8501. Min Act: -0.0002

Data Index: 953119 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.8542. Min Act: -0.0002

Data Index: 1091379 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.7586. Min Act: -0.0002

Data Index: 416146 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.8997. Min Act: -0.0002

Data Index: 995538 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.9170. Min Act: -0.0002

Data Index: 766667 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.8385. Min Act: -0.0002

Data Index: 676304 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.7856. Min Act: -0.0002

Data Index: 297219 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.7812. Min Act: -0.0002

Data Index: 1212943 (C4 (Web Text))

Max Activating Token Index: 139