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

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

Neuron 5160 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: 0.6621. Min Range: -0.6621

Max Act: 0.6621. Min Act: -0.0000

Data Index: 303326 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.6614. Min Act: -0.0000

Data Index: 192604 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4905. Min Act: -0.0000

Data Index: 80115 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.5096. Min Act: -0.0000

Data Index: 959639 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4899. Min Act: -0.0000

Data Index: 708080 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4283. Min Act: -0.0000

Data Index: 797385 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4091. Min Act: -0.0000

Data Index: 60634 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3917. Min Act: -0.0000

Data Index: 2329 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3933. Min Act: -0.0000

Data Index: 300479 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3998. Min Act: -0.0000

Data Index: 644559 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3882. Min Act: 0.0000

Data Index: 1087713 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3884. Min Act: -0.0000

Data Index: 125152 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1188398 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3863. Min Act: -0.0000

Data Index: 398413 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3575. Min Act: -0.0000

Data Index: 577743 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3498. Min Act: -0.0000

Data Index: 145283 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1150849 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1340392 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3654. Min Act: -0.0000

Data Index: 182423 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3611. Min Act: -0.0000

Data Index: 826950 (C4 (Web Text))

Max Activating Token Index: 996