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

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

Neuron 2381 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.7832. Min Act: -0.0001

Data Index: 179189 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.6170. Min Act: -0.0001

Data Index: 1251449 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.6820. Min Act: -0.0001

Data Index: 494926 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.7028. Min Act: -0.0001

Data Index: 1129083 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.4563. Min Act: -0.0000

Data Index: 756307 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.3189. Min Act: -0.0001

Data Index: 381303 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.3520. Min Act: -0.0001

Data Index: 566306 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.2708. Min Act: -0.0001

Data Index: 1021194 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.2281. Min Act: -0.0001

Data Index: 388943 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.2223. Min Act: -0.0001

Data Index: 1583977 (Python Code)

Max Activating Token Index: 562

Text #10

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.2408. Min Act: -0.0001

Data Index: 329589 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.2115. Min Act: -0.0001

Data Index: 1085857 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.2101. Min Act: -0.0001

Data Index: 1397390 (Python Code)

Max Activating Token Index: 33

Text #13

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.2066. Min Act: -0.0001

Data Index: 432364 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.1999. Min Act: -0.0001

Data Index: 1655557 (Python Code)

Max Activating Token Index: 601

Text #15

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.1986. Min Act: -0.0001

Data Index: 206193 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.1799. Min Act: -0.0001

Data Index: 1577670 (Python Code)

Max Activating Token Index: 585

Text #17

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.2091. Min Act: -0.0001

Data Index: 550838 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.1329. Min Act: -0.0001

Data Index: 622170 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 1.7832. Min Range: -1.7832

Max Act: 1.1648. Min Act: -0.0001

Data Index: 464425 (C4 (Web Text))

Max Activating Token Index: 863