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

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

Neuron 3110 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5481. Min Range: -2.5481

Max Act: 2.5481. Min Act: -0.0000

Data Index: 275375 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 2.5481. Min Range: -2.5481

Max Act: 2.3490. Min Act: -0.0000

Data Index: 667686 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 2.5481. Min Range: -2.5481

Max Act: 2.3387. Min Act: -0.0000

Data Index: 68709 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 2.5481. Min Range: -2.5481

Max Act: 2.2264. Min Act: -0.0000

Data Index: 118920 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 2.5481. Min Range: -2.5481

Max Act: 2.2215. Min Act: -0.0000

Data Index: 628629 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 2.5481. Min Range: -2.5481

Max Act: 2.1078. Min Act: -0.0000

Data Index: 325207 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 2.5481. Min Range: -2.5481

Max Act: 1.9712. Min Act: -0.0000

Data Index: 782942 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 2.5481. Min Range: -2.5481

Max Act: 2.0527. Min Act: -0.0000

Data Index: 847827 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 2.5481. Min Range: -2.5481

Max Act: 1.7956. Min Act: -0.0000

Data Index: 274252 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 2.5481. Min Range: -2.5481

Max Act: 1.8736. Min Act: -0.0000

Data Index: 739273 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 2.5481. Min Range: -2.5481

Max Act: 1.8180. Min Act: -0.0000

Data Index: 262557 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 2.5481. Min Range: -2.5481

Max Act: 1.8367. Min Act: -0.0000

Data Index: 802550 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 2.5481. Min Range: -2.5481

Max Act: 1.7191. Min Act: -0.0000

Data Index: 768870 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 2.5481. Min Range: -2.5481

Max Act: 1.7558. Min Act: -0.0000

Data Index: 531362 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 2.5481. Min Range: -2.5481

Max Act: 1.6729. Min Act: -0.0001

Data Index: 1164483 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 2.5481. Min Range: -2.5481

Max Act: 1.5936. Min Act: -0.0000

Data Index: 744207 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 2.5481. Min Range: -2.5481

Max Act: 1.7388. Min Act: -0.0000

Data Index: 364030 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 2.5481. Min Range: -2.5481

Max Act: 1.6464. Min Act: -0.0000

Data Index: 1324228 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 2.5481. Min Range: -2.5481

Max Act: 1.7164. Min Act: -0.0000

Data Index: 888591 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 2.5481. Min Range: -2.5481

Max Act: 1.7711. Min Act: -0.0000

Data Index: 1234811 (C4 (Web Text))

Max Activating Token Index: 999