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

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

Neuron 2969 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.3641. Min Act: -0.0001

Data Index: 428178 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.3540. Min Act: -0.0002

Data Index: 825115 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.3415. Min Act: -0.0001

Data Index: 705907 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.2011. Min Act: -0.0001

Data Index: 471759 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.2572. Min Act: -0.0001

Data Index: 481145 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.1819. Min Act: -0.0002

Data Index: 63500 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.2306. Min Act: -0.0001

Data Index: 201655 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.1403. Min Act: -0.0002

Data Index: 486254 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.2076. Min Act: -0.0001

Data Index: 599714 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.0762. Min Act: -0.0001

Data Index: 595210 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.1270. Min Act: -0.0001

Data Index: 74564 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.0461. Min Act: -0.0001

Data Index: 1354888 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.1388. Min Act: -0.0002

Data Index: 1225079 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.0985. Min Act: -0.0001

Data Index: 714537 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.1213. Min Act: -0.0001

Data Index: 368557 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.1192. Min Act: -0.0001

Data Index: 1186265 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.1459. Min Act: -0.0001

Data Index: 1183096 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.1009. Min Act: -0.0001

Data Index: 1313510 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.0626. Min Act: -0.0002

Data Index: 312694 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 1.3641. Min Range: -1.3641

Max Act: 1.0892. Min Act: -0.0001

Data Index: 1153244 (C4 (Web Text))

Max Activating Token Index: 138