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

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

Neuron 1938 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.5798. Min Act: -0.0001

Data Index: 251738 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.4750. Min Act: -0.0001

Data Index: 304584 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.4995. Min Act: -0.0001

Data Index: 29381 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.5032. Min Act: -0.0001

Data Index: 162900 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.5888. Min Act: -0.0001

Data Index: 26259 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.4256. Min Act: -0.0001

Data Index: 1003570 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.4436. Min Act: -0.0001

Data Index: 1147674 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.4901. Min Act: -0.0001

Data Index: 932916 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.4921. Min Act: -0.0001

Data Index: 1334783 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.4280. Min Act: -0.0001

Data Index: 842298 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.4509. Min Act: -0.0001

Data Index: 1232007 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.4923. Min Act: -0.0001

Data Index: 347938 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.3780. Min Act: -0.0001

Data Index: 295080 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.4478. Min Act: -0.0001

Data Index: 785960 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.3137. Min Act: -0.0001

Data Index: 1073682 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.4305. Min Act: -0.0001

Data Index: 946184 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.3333. Min Act: -0.0001

Data Index: 822145 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.2997. Min Act: -0.0001

Data Index: 1198576 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.3156. Min Act: -0.0001

Data Index: 1346518 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 1.5888. Min Range: -1.5888

Max Act: 1.3918. Min Act: -0.0001

Data Index: 184053 (C4 (Web Text))

Max Activating Token Index: 595