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

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

Neuron 1038 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6986. Min Act: -0.0000

Data Index: 736527 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6448. Min Act: -0.0001

Data Index: 390683 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6419. Min Act: -0.0001

Data Index: 464944 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5238. Min Act: -0.0000

Data Index: 789578 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5547. Min Act: -0.0000

Data Index: 1186975 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5559. Min Act: -0.0001

Data Index: 194258 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5072. Min Act: -0.0000

Data Index: 573706 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5402. Min Act: -0.0001

Data Index: 231218 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5317. Min Act: -0.0000

Data Index: 682692 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5454. Min Act: -0.0001

Data Index: 942737 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5291. Min Act: -0.0000

Data Index: 414791 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5052. Min Act: -0.0000

Data Index: 704276 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5180. Min Act: -0.0000

Data Index: 838492 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.4907. Min Act: -0.0001

Data Index: 902348 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5064. Min Act: -0.0001

Data Index: 110223 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.4931. Min Act: -0.0000

Data Index: 504249 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.4657. Min Act: -0.0001

Data Index: 449865 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5029. Min Act: -0.0001

Data Index: 1169726 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5160. Min Act: -0.0001

Data Index: 309245 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.4939. Min Act: -0.0001

Data Index: 954372 (C4 (Web Text))

Max Activating Token Index: 700