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

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

Neuron 1991 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1466523 (Python Code)

Max Activating Token Index: 295

Text #1

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1499936 (Python Code)

Max Activating Token Index: 542

Text #2

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1212. Min Act: -0.0001

Data Index: 578946 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1238. Min Act: -0.0001

Data Index: 1551516 (Python Code)

Max Activating Token Index: 411

Text #4

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1542439 (Python Code)

Max Activating Token Index: 841

Text #5

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1139. Min Act: -0.0001

Data Index: 1638536 (Python Code)

Max Activating Token Index: 886

Text #6

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1076. Min Act: -0.0001

Data Index: 1445789 (Python Code)

Max Activating Token Index: 243

Text #7

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1029. Min Act: -0.0001

Data Index: 467346 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1050. Min Act: -0.0001

Data Index: 1537421 (Python Code)

Max Activating Token Index: 795

Text #9

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0954. Min Act: -0.0001

Data Index: 347708 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0972. Min Act: -0.0001

Data Index: 850281 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0957. Min Act: -0.0001

Data Index: 467795 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0992. Min Act: -0.0001

Data Index: 1561670 (Python Code)

Max Activating Token Index: 987

Text #13

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1501405 (Python Code)

Max Activating Token Index: 100

Text #14

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0969. Min Act: -0.0001

Data Index: 1439839 (Python Code)

Max Activating Token Index: 790

Text #15

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0952. Min Act: -0.0001

Data Index: 542080 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0944. Min Act: -0.0001

Data Index: 499214 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0948. Min Act: -0.0001

Data Index: 895069 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1015. Min Act: -0.0001

Data Index: 793675 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0985. Min Act: -0.0001

Data Index: 60995 (C4 (Web Text))

Max Activating Token Index: 261