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

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

Neuron 1930 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1402. Min Range: -3.1402

Max Act: 3.1402. Min Act: -0.0000

Data Index: 75173 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.8056. Min Act: -0.0000

Data Index: 1253881 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.7440. Min Act: -0.0000

Data Index: 796780 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.6123. Min Act: -0.0000

Data Index: 3748 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.6114. Min Act: -0.0000

Data Index: 358695 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.6595. Min Act: -0.0000

Data Index: 101172 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.6937. Min Act: -0.0000

Data Index: 197358 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.6543. Min Act: -0.0000

Data Index: 671446 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.7337. Min Act: -0.0000

Data Index: 1217709 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.4687. Min Act: -0.0000

Data Index: 848386 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.5103. Min Act: -0.0000

Data Index: 752090 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.4538. Min Act: -0.0000

Data Index: 692982 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.3307. Min Act: -0.0000

Data Index: 374846 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.4229. Min Act: -0.0000

Data Index: 721647 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.4125. Min Act: -0.0000

Data Index: 978157 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.4164. Min Act: -0.0000

Data Index: 443422 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.3965. Min Act: -0.0000

Data Index: 1048554 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.2655. Min Act: -0.0000

Data Index: 736474 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.3935. Min Act: -0.0000

Data Index: 979998 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.2583. Min Act: -0.0000

Data Index: 60299 (C4 (Web Text))

Max Activating Token Index: 172