Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3858 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.4473. Min Act: -0.0001

Data Index: 952434 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.4710. Min Act: -0.0000

Data Index: 1001090 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.4450. Min Act: -0.0001

Data Index: 573755 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.3096. Min Act: -0.0000

Data Index: 1355544 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.2945. Min Act: -0.0001

Data Index: 1019905 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.2855. Min Act: -0.0001

Data Index: 910674 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.3254. Min Act: -0.0001

Data Index: 954880 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.4874. Min Act: -0.0000

Data Index: 1141281 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.3477. Min Act: -0.0001

Data Index: 152866 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.3517. Min Act: -0.0001

Data Index: 1556987 (Python Code)

Max Activating Token Index: 995

Text #10

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.3362. Min Act: -0.0001

Data Index: 1255712 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.3406. Min Act: -0.0001

Data Index: 629761 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.3836. Min Act: -0.0001

Data Index: 1048507 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.4381. Min Act: -0.0001

Data Index: 878711 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.4089. Min Act: -0.0000

Data Index: 540874 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.3048. Min Act: -0.0000

Data Index: 311229 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.3540. Min Act: -0.0001

Data Index: 230039 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.3581. Min Act: -0.0000

Data Index: 269631 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.3318. Min Act: -0.0001

Data Index: 236795 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 1.4874. Min Range: -1.4874

Max Act: 1.3460. Min Act: -0.0000

Data Index: 883979 (C4 (Web Text))

Max Activating Token Index: 213