Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4683 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8023. Min Range: -1.8023

Max Act: 1.8023. Min Act: -0.0000

Data Index: 1170617 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 1.8023. Min Range: -1.8023

Max Act: 1.5272. Min Act: -0.0000

Data Index: 661985 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 1.8023. Min Range: -1.8023

Max Act: 1.2489. Min Act: -0.0000

Data Index: 149324 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 1.8023. Min Range: -1.8023

Max Act: 1.4374. Min Act: -0.0000

Data Index: 429978 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 1.8023. Min Range: -1.8023

Max Act: 1.1369. Min Act: -0.0000

Data Index: 995965 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 1.8023. Min Range: -1.8023

Max Act: 1.1320. Min Act: -0.0000

Data Index: 800156 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 1.8023. Min Range: -1.8023

Max Act: 1.0994. Min Act: -0.0000

Data Index: 461836 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 1.8023. Min Range: -1.8023

Max Act: 1.1722. Min Act: -0.0000

Data Index: 422557 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 1.8023. Min Range: -1.8023

Max Act: 1.1293. Min Act: -0.0000

Data Index: 390112 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 1.8023. Min Range: -1.8023

Max Act: 1.0528. Min Act: -0.0000

Data Index: 572786 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 1.8023. Min Range: -1.8023

Max Act: 1.0587. Min Act: -0.0000

Data Index: 310806 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 1.8023. Min Range: -1.8023

Max Act: 1.0619. Min Act: -0.0000

Data Index: 316002 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 1.8023. Min Range: -1.8023

Max Act: 0.9552. Min Act: -0.0000

Data Index: 132747 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 1.8023. Min Range: -1.8023

Max Act: 1.0257. Min Act: -0.0000

Data Index: 1133689 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 1.8023. Min Range: -1.8023

Max Act: 0.9647. Min Act: -0.0000

Data Index: 621176 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 1.8023. Min Range: -1.8023

Max Act: 0.9596. Min Act: -0.0000

Data Index: 788149 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 1.8023. Min Range: -1.8023

Max Act: 1.0401. Min Act: -0.0000

Data Index: 72974 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 1.8023. Min Range: -1.8023

Max Act: 1.0364. Min Act: -0.0000

Data Index: 1132389 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 1.8023. Min Range: -1.8023

Max Act: 1.0110. Min Act: -0.0000

Data Index: 316450 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 1.8023. Min Range: -1.8023

Max Act: 0.9640. Min Act: -0.0000

Data Index: 1146896 (C4 (Web Text))

Max Activating Token Index: 33