Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3902 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.4260. Min Act: -0.0001

Data Index: 691990 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.2269. Min Act: -0.0001

Data Index: 409977 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.2614. Min Act: -0.0001

Data Index: 1236483 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.2450. Min Act: -0.0001

Data Index: 350906 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.1712. Min Act: -0.0001

Data Index: 914000 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.1624. Min Act: -0.0001

Data Index: 608 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.1248. Min Act: -0.0001

Data Index: 6816 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.0895. Min Act: -0.0001

Data Index: 993374 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.0529. Min Act: -0.0001

Data Index: 378822 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.1209. Min Act: -0.0001

Data Index: 1323790 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.0918. Min Act: -0.0001

Data Index: 1154643 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.1163. Min Act: -0.0001

Data Index: 167506 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.0463. Min Act: -0.0001

Data Index: 1346934 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.0477. Min Act: -0.0001

Data Index: 1272965 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.0724. Min Act: -0.0001

Data Index: 1136911 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.0682. Min Act: -0.0001

Data Index: 873370 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 1.4260. Min Range: -1.4260

Max Act: 0.9978. Min Act: -0.0001

Data Index: 116935 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.0560. Min Act: -0.0001

Data Index: 1090838 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.0056. Min Act: -0.0001

Data Index: 429619 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 1.4260. Min Range: -1.4260

Max Act: 1.0077. Min Act: -0.0001

Data Index: 1160811 (C4 (Web Text))

Max Activating Token Index: 29