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

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

Neuron 2314 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8543. Min Act: -0.0001

Data Index: 428706 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.9508. Min Act: -0.0001

Data Index: 668728 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8988. Min Act: -0.0000

Data Index: 913715 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8805. Min Act: -0.0000

Data Index: 1095290 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1263025 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8291. Min Act: -0.0000

Data Index: 497559 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8538. Min Act: -0.0000

Data Index: 259433 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8477. Min Act: -0.0000

Data Index: 851253 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8415. Min Act: -0.0001

Data Index: 1215181 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8256. Min Act: -0.0000

Data Index: 671904 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7422. Min Act: -0.0000

Data Index: 444084 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8458. Min Act: -0.0000

Data Index: 561207 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7913. Min Act: -0.0000

Data Index: 848020 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8046. Min Act: -0.0000

Data Index: 61346 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7997. Min Act: -0.0000

Data Index: 475808 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1071067 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8023. Min Act: -0.0000

Data Index: 247465 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8250. Min Act: -0.0001

Data Index: 1307836 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1267308 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1059785 (C4 (Web Text))

Max Activating Token Index: 857