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

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

Neuron 700 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6935. Min Act: -0.0000

Data Index: 662891 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6801. Min Act: -0.0000

Data Index: 596608 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6315. Min Act: -0.0000

Data Index: 1157073 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6499. Min Act: -0.0000

Data Index: 608274 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6395. Min Act: -0.0000

Data Index: 926900 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6520. Min Act: -0.0000

Data Index: 669942 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1138621 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6422. Min Act: -0.0000

Data Index: 924928 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6034. Min Act: -0.0000

Data Index: 298392 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1298223 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5666. Min Act: -0.0000

Data Index: 619068 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5692. Min Act: -0.0000

Data Index: 226372 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1053962 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5508. Min Act: -0.0000

Data Index: 394413 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5642. Min Act: -0.0000

Data Index: 747423 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5244. Min Act: -0.0000

Data Index: 618427 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5248. Min Act: -0.0000

Data Index: 229309 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5294. Min Act: -0.0000

Data Index: 151357 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.4903. Min Act: -0.0000

Data Index: 208761 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5078. Min Act: -0.0000

Data Index: 37427 (C4 (Web Text))

Max Activating Token Index: 458