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

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

Neuron 3473 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2081. Min Range: -7.2081

Max Act: 7.2081. Min Act: -0.0000

Data Index: 198548 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.8821. Min Act: -0.0000

Data Index: 1182913 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.4166. Min Act: -0.0000

Data Index: 119771 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.3645. Min Act: -0.0000

Data Index: 678041 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 7.2081. Min Range: -7.2081

Max Act: 6.4437. Min Act: -0.0000

Data Index: 742612 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 7.2081. Min Range: -7.2081

Max Act: 5.6194. Min Act: -0.0000

Data Index: 85584 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 7.2081. Min Range: -7.2081

Max Act: 5.5329. Min Act: -0.0000

Data Index: 342025 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 7.2081. Min Range: -7.2081

Max Act: 5.4866. Min Act: -0.0000

Data Index: 1255859 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 7.2081. Min Range: -7.2081

Max Act: 5.5802. Min Act: -0.0000

Data Index: 284371 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 7.2081. Min Range: -7.2081

Max Act: 5.3729. Min Act: -0.0000

Data Index: 76355 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 7.2081. Min Range: -7.2081

Max Act: 5.3493. Min Act: -0.0000

Data Index: 1116988 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 7.2081. Min Range: -7.2081

Max Act: 5.3028. Min Act: -0.0000

Data Index: 62585 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 7.2081. Min Range: -7.2081

Max Act: 4.9543. Min Act: -0.0000

Data Index: 669144 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 7.2081. Min Range: -7.2081

Max Act: 4.9479. Min Act: -0.0000

Data Index: 203612 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 7.2081. Min Range: -7.2081

Max Act: 5.1051. Min Act: -0.0000

Data Index: 1267033 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 7.2081. Min Range: -7.2081

Max Act: 4.8848. Min Act: -0.0000

Data Index: 1277811 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 7.2081. Min Range: -7.2081

Max Act: 5.0856. Min Act: 0.0000

Data Index: 580422 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 7.2081. Min Range: -7.2081

Max Act: 4.9901. Min Act: -0.0000

Data Index: 545607 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 7.2081. Min Range: -7.2081

Max Act: 4.8256. Min Act: -0.0000

Data Index: 603463 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 7.2081. Min Range: -7.2081

Max Act: 4.7051. Min Act: -0.0000

Data Index: 61408 (C4 (Web Text))

Max Activating Token Index: 687