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

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

Neuron 20 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: 3.2220. Min Range: -3.2220

Max Act: 3.2220. Min Act: -0.0000

Data Index: 821735 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 3.2220. Min Range: -3.2220

Max Act: 3.1827. Min Act: -0.0000

Data Index: 46760 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 3.2220. Min Range: -3.2220

Max Act: 3.0774. Min Act: -0.0000

Data Index: 114333 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 3.2220. Min Range: -3.2220

Max Act: 2.5815. Min Act: -0.0000

Data Index: 923171 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 3.2220. Min Range: -3.2220

Max Act: 2.6518. Min Act: -0.0000

Data Index: 33096 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 3.2220. Min Range: -3.2220

Max Act: 2.7252. Min Act: -0.0000

Data Index: 1188909 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 3.2220. Min Range: -3.2220

Max Act: 2.4038. Min Act: -0.0000

Data Index: 230066 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 3.2220. Min Range: -3.2220

Max Act: 2.5408. Min Act: -0.0000

Data Index: 1102561 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 3.2220. Min Range: -3.2220

Max Act: 2.6099. Min Act: -0.0000

Data Index: 452025 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 3.2220. Min Range: -3.2220

Max Act: 2.5933. Min Act: -0.0000

Data Index: 795143 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 3.2220. Min Range: -3.2220

Max Act: 2.4480. Min Act: -0.0000

Data Index: 1027130 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 3.2220. Min Range: -3.2220

Max Act: 2.3985. Min Act: -0.0000

Data Index: 585225 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 3.2220. Min Range: -3.2220

Max Act: 2.3765. Min Act: -0.0000

Data Index: 93974 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 3.2220. Min Range: -3.2220

Max Act: 2.3856. Min Act: -0.0000

Data Index: 498430 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 3.2220. Min Range: -3.2220

Max Act: 2.3850. Min Act: -0.0000

Data Index: 1315675 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 3.2220. Min Range: -3.2220

Max Act: 2.4754. Min Act: -0.0000

Data Index: 89350 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 3.2220. Min Range: -3.2220

Max Act: 2.2536. Min Act: -0.0000

Data Index: 1119603 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 3.2220. Min Range: -3.2220

Max Act: 2.2341. Min Act: -0.0000

Data Index: 666287 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 3.2220. Min Range: -3.2220

Max Act: 2.3520. Min Act: -0.0000

Data Index: 445914 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 3.2220. Min Range: -3.2220

Max Act: 2.1073. Min Act: -0.0000

Data Index: 180416 (C4 (Web Text))

Max Activating Token Index: 817