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

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

Neuron 1908 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.8286. Min Act: -0.0001

Data Index: 217698 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.8084. Min Act: -0.0001

Data Index: 983696 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.8239. Min Act: -0.0001

Data Index: 333170 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.7532. Min Act: -0.0001

Data Index: 997537 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.8305. Min Act: -0.0001

Data Index: 635017 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.7811. Min Act: -0.0001

Data Index: 946426 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.7623. Min Act: -0.0001

Data Index: 94635 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.5928. Min Act: -0.0001

Data Index: 296450 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.6929. Min Act: -0.0001

Data Index: 894990 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.7757. Min Act: -0.0001

Data Index: 489225 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.7130. Min Act: -0.0001

Data Index: 1231107 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.7422. Min Act: -0.0001

Data Index: 937461 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.6391. Min Act: -0.0001

Data Index: 472769 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.8119. Min Act: -0.0001

Data Index: 175369 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.5570. Min Act: -0.0001

Data Index: 1348686 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.5984. Min Act: -0.0001

Data Index: 80478 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.6068. Min Act: -0.0001

Data Index: 1064969 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.6485. Min Act: -0.0001

Data Index: 736314 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.5510. Min Act: -0.0001

Data Index: 13 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 1.8305. Min Range: -1.8305

Max Act: 1.4820. Min Act: -0.0001

Data Index: 134701 (C4 (Web Text))

Max Activating Token Index: 678