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

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

Neuron 2922 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8080. Min Range: -4.8080

Max Act: 4.8080. Min Act: -0.0000

Data Index: 541580 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 4.8080. Min Range: -4.8080

Max Act: 4.7875. Min Act: -0.0000

Data Index: 519440 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 4.8080. Min Range: -4.8080

Max Act: 4.6481. Min Act: -0.0000

Data Index: 637840 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 4.8080. Min Range: -4.8080

Max Act: 4.1973. Min Act: -0.0000

Data Index: 708730 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 4.8080. Min Range: -4.8080

Max Act: 4.2673. Min Act: -0.0000

Data Index: 518067 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 4.8080. Min Range: -4.8080

Max Act: 3.8979. Min Act: -0.0000

Data Index: 600372 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 4.8080. Min Range: -4.8080

Max Act: 3.9267. Min Act: -0.0000

Data Index: 963127 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 4.8080. Min Range: -4.8080

Max Act: 3.6251. Min Act: -0.0000

Data Index: 1156802 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 4.8080. Min Range: -4.8080

Max Act: 3.6361. Min Act: -0.0000

Data Index: 901906 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 4.8080. Min Range: -4.8080

Max Act: 3.8812. Min Act: -0.0000

Data Index: 83992 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 4.8080. Min Range: -4.8080

Max Act: 3.4721. Min Act: -0.0000

Data Index: 466235 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 4.8080. Min Range: -4.8080

Max Act: 3.4821. Min Act: -0.0000

Data Index: 1127538 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 4.8080. Min Range: -4.8080

Max Act: 3.4616. Min Act: -0.0000

Data Index: 1124263 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 4.8080. Min Range: -4.8080

Max Act: 3.4543. Min Act: -0.0000

Data Index: 796102 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 4.8080. Min Range: -4.8080

Max Act: 3.6058. Min Act: -0.0000

Data Index: 1312200 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 4.8080. Min Range: -4.8080

Max Act: 3.2739. Min Act: -0.0000

Data Index: 721124 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 4.8080. Min Range: -4.8080

Max Act: 3.4058. Min Act: -0.0000

Data Index: 284490 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 4.8080. Min Range: -4.8080

Max Act: 3.4928. Min Act: -0.0000

Data Index: 1207865 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 4.8080. Min Range: -4.8080

Max Act: 3.6139. Min Act: -0.0000

Data Index: 855057 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 4.8080. Min Range: -4.8080

Max Act: 3.2670. Min Act: -0.0000

Data Index: 1054277 (C4 (Web Text))

Max Activating Token Index: 280