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

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

Neuron 3547 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: 5.1314. Min Range: -5.1314

Max Act: 5.1314. Min Act: -0.0000

Data Index: 105058 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.3456. Min Act: -0.0000

Data Index: 428895 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.3536. Min Act: -0.0000

Data Index: 456965 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.1858. Min Act: -0.0000

Data Index: 1359631 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.0073. Min Act: -0.0000

Data Index: 1027869 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 5.1314. Min Range: -5.1314

Max Act: 3.5074. Min Act: -0.0000

Data Index: 987160 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 5.1314. Min Range: -5.1314

Max Act: 2.9077. Min Act: -0.0000

Data Index: 22200 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 5.1314. Min Range: -5.1314

Max Act: 3.1727. Min Act: -0.0000

Data Index: 129891 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 5.1314. Min Range: -5.1314

Max Act: 2.5398. Min Act: -0.0000

Data Index: 468674 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 5.1314. Min Range: -5.1314

Max Act: 2.7668. Min Act: -0.0000

Data Index: 786358 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 5.1314. Min Range: -5.1314

Max Act: 2.6331. Min Act: -0.0000

Data Index: 592202 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 5.1314. Min Range: -5.1314

Max Act: 2.9022. Min Act: -0.0000

Data Index: 70916 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 5.1314. Min Range: -5.1314

Max Act: 2.5371. Min Act: -0.0000

Data Index: 299351 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 5.1314. Min Range: -5.1314

Max Act: 2.6792. Min Act: -0.0000

Data Index: 331026 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 5.1314. Min Range: -5.1314

Max Act: 2.3994. Min Act: -0.0000

Data Index: 893337 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 5.1314. Min Range: -5.1314

Max Act: 2.3146. Min Act: -0.0000

Data Index: 1297321 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 5.1314. Min Range: -5.1314

Max Act: 2.8421. Min Act: -0.0000

Data Index: 626243 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 5.1314. Min Range: -5.1314

Max Act: 2.4741. Min Act: -0.0000

Data Index: 926835 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 5.1314. Min Range: -5.1314

Max Act: 2.5947. Min Act: -0.0000

Data Index: 764716 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 5.1314. Min Range: -5.1314

Max Act: 2.7539. Min Act: -0.0000

Data Index: 1036771 (C4 (Web Text))

Max Activating Token Index: 325