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

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

Neuron 1150 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.7146. Min Act: -0.0000

Data Index: 559330 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.5264. Min Act: -0.0000

Data Index: 671283 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.6423. Min Act: -0.0000

Data Index: 24498 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.3336. Min Act: -0.0000

Data Index: 974209 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.4088. Min Act: -0.0000

Data Index: 183657 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.3326. Min Act: -0.0000

Data Index: 526543 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.4304. Min Act: -0.0000

Data Index: 1089144 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.3307. Min Act: -0.0001

Data Index: 244623 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.0988. Min Act: -0.0000

Data Index: 143334 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.2567. Min Act: -0.0000

Data Index: 176316 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.2405. Min Act: -0.0000

Data Index: 813321 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.3153. Min Act: -0.0000

Data Index: 938479 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.1880. Min Act: -0.0000

Data Index: 1244621 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.2922. Min Act: -0.0001

Data Index: 553781 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.3665. Min Act: -0.0000

Data Index: 1298704 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.2739. Min Act: -0.0000

Data Index: 420876 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.1827. Min Act: -0.0000

Data Index: 699219 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.2888. Min Act: -0.0000

Data Index: 1053421 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.2627. Min Act: -0.0000

Data Index: 966549 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 1.7146. Min Range: -1.7146

Max Act: 1.2097. Min Act: -0.0000

Data Index: 904298 (C4 (Web Text))

Max Activating Token Index: 689