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

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

Neuron 4533 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: 0.2161. Min Range: -0.2161

Max Act: 0.1926. Min Act: -0.0001

Data Index: 306228 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.2161. Min Act: -0.0001

Data Index: 527415 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.2091. Min Act: -0.0001

Data Index: 1312044 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1876. Min Act: -0.0001

Data Index: 1007647 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1012326 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1848. Min Act: -0.0001

Data Index: 821403 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1958. Min Act: -0.0001

Data Index: 723440 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1703. Min Act: -0.0001

Data Index: 1323961 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1844. Min Act: -0.0001

Data Index: 600941 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1518. Min Act: -0.0001

Data Index: 402952 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1708. Min Act: -0.0001

Data Index: 106731 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1700. Min Act: -0.0001

Data Index: 698105 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1605. Min Act: -0.0001

Data Index: 687526 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1538. Min Act: -0.0001

Data Index: 37587 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1544. Min Act: -0.0001

Data Index: 367753 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1260. Min Act: -0.0001

Data Index: 19568 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1621. Min Act: -0.0001

Data Index: 728888 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1325. Min Act: -0.0001

Data Index: 165658 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1600. Min Act: -0.0001

Data Index: 1315012 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.2161. Min Range: -0.2161

Max Act: 0.1590. Min Act: -0.0001

Data Index: 1189765 (C4 (Web Text))

Max Activating Token Index: 448