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

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

Neuron 2286 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: 3.2497. Min Range: -3.2497

Max Act: 3.2497. Min Act: -0.0001

Data Index: 1069580 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 3.2497. Min Range: -3.2497

Max Act: 3.0212. Min Act: -0.0001

Data Index: 759877 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 3.2497. Min Range: -3.2497

Max Act: 3.1894. Min Act: -0.0001

Data Index: 695365 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.9086. Min Act: -0.0001

Data Index: 857292 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.6952. Min Act: -0.0001

Data Index: 1100813 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.9215. Min Act: -0.0001

Data Index: 1429917 (Python Code)

Max Activating Token Index: 120

Text #6

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.7793. Min Act: -0.0001

Data Index: 639455 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.6629. Min Act: -0.0001

Data Index: 1430865 (Python Code)

Max Activating Token Index: 748

Text #8

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.5040. Min Act: -0.0001

Data Index: 992308 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.4845. Min Act: -0.0001

Data Index: 1425751 (Python Code)

Max Activating Token Index: 26

Text #10

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.3912. Min Act: -0.0001

Data Index: 874235 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.4968. Min Act: -0.0001

Data Index: 392832 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.2294. Min Act: -0.0001

Data Index: 1073752 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.3343. Min Act: -0.0001

Data Index: 1047227 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.4266. Min Act: -0.0001

Data Index: 555404 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.2175. Min Act: -0.0001

Data Index: 269249 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.2039. Min Act: -0.0001

Data Index: 46214 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.0803. Min Act: -0.0001

Data Index: 951394 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 3.2497. Min Range: -3.2497

Max Act: 2.1860. Min Act: -0.0001

Data Index: 1537791 (Python Code)

Max Activating Token Index: 765

Text #19

Max Range: 3.2497. Min Range: -3.2497

Max Act: 1.7344. Min Act: -0.0001

Data Index: 1244235 (C4 (Web Text))

Max Activating Token Index: 841