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

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

Neuron 781 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: 2.0134. Min Range: -2.0134

Max Act: 1.9815. Min Act: -0.0000

Data Index: 695530 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 2.0134. Min Range: -2.0134

Max Act: 1.9103. Min Act: -0.0000

Data Index: 593230 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 2.0134. Min Range: -2.0134

Max Act: 1.7020. Min Act: -0.0000

Data Index: 1265431 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 2.0134. Min Range: -2.0134

Max Act: 1.9456. Min Act: -0.0000

Data Index: 1125658 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 2.0134. Min Range: -2.0134

Max Act: 1.6725. Min Act: -0.0000

Data Index: 597422 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 2.0134. Min Range: -2.0134

Max Act: 2.0134. Min Act: -0.0000

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 2.0134. Min Range: -2.0134

Max Act: 1.5014. Min Act: -0.0000

Data Index: 375657 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 2.0134. Min Range: -2.0134

Max Act: 1.4632. Min Act: -0.0000

Data Index: 104970 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 2.0134. Min Range: -2.0134

Max Act: 1.6331. Min Act: -0.0000

Data Index: 1360579 (Python Code)

Max Activating Token Index: 848

Text #9

Max Range: 2.0134. Min Range: -2.0134

Max Act: 1.4620. Min Act: -0.0000

Data Index: 1154569 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 2.0134. Min Range: -2.0134

Max Act: 1.4883. Min Act: -0.0000

Data Index: 662311 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 2.0134. Min Range: -2.0134

Max Act: 1.4513. Min Act: -0.0000

Data Index: 853939 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 2.0134. Min Range: -2.0134

Max Act: 1.4735. Min Act: -0.0000

Data Index: 197284 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 2.0134. Min Range: -2.0134

Max Act: 1.3881. Min Act: -0.0000

Data Index: 98537 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 2.0134. Min Range: -2.0134

Max Act: 1.5400. Min Act: -0.0000

Data Index: 1191763 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 2.0134. Min Range: -2.0134

Max Act: 1.3311. Min Act: -0.0000

Data Index: 532741 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 2.0134. Min Range: -2.0134

Max Act: 1.4373. Min Act: -0.0000

Data Index: 849425 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 2.0134. Min Range: -2.0134

Max Act: 1.3920. Min Act: -0.0000

Data Index: 1301765 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 2.0134. Min Range: -2.0134

Max Act: 1.3365. Min Act: -0.0000

Data Index: 1347506 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 2.0134. Min Range: -2.0134

Max Act: 1.4031. Min Act: -0.0000

Data Index: 27961 (C4 (Web Text))

Max Activating Token Index: 788