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

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

Neuron 3878 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.8978. Min Act: -0.0000

Data Index: 401915 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.8968. Min Act: -0.0001

Data Index: 298083 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.8167. Min Act: -0.0000

Data Index: 406272 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.7290. Min Act: -0.0001

Data Index: 1294873 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.8269. Min Act: -0.0000

Data Index: 3297 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.7069. Min Act: -0.0001

Data Index: 635585 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.6362. Min Act: -0.0001

Data Index: 1189622 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.6261. Min Act: -0.0000

Data Index: 1354219 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.6609. Min Act: -0.0000

Data Index: 1097397 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.6977. Min Act: -0.0001

Data Index: 34562 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.7041. Min Act: -0.0000

Data Index: 41309 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.6057. Min Act: -0.0001

Data Index: 689603 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.5849. Min Act: -0.0000

Data Index: 237849 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.6449. Min Act: -0.0000

Data Index: 714339 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.5980. Min Act: -0.0001

Data Index: 1062578 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.5402. Min Act: -0.0000

Data Index: 683150 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.5966. Min Act: -0.0001

Data Index: 226238 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.5740. Min Act: -0.0000

Data Index: 112906 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.4991. Min Act: -0.0000

Data Index: 686623 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.5882. Min Act: -0.0001

Data Index: 214623 (C4 (Web Text))

Max Activating Token Index: 743