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

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

Neuron 4875 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.8505. Min Act: -0.0000

Data Index: 1199867 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6771. Min Act: -0.0000

Data Index: 1237208 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.4819. Min Act: -0.0000

Data Index: 121329 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.3200. Min Act: -0.0000

Data Index: 535201 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.3328. Min Act: -0.0000

Data Index: 1251781 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.3451. Min Act: -0.0000

Data Index: 799939 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.3214. Min Act: -0.0000

Data Index: 577684 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.3274. Min Act: -0.0000

Data Index: 247177 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1363182 (Python Code)

Max Activating Token Index: 253

Text #9

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.3139. Min Act: -0.0000

Data Index: 591661 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.3225. Min Act: -0.0000

Data Index: 312827 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.3045. Min Act: -0.0000

Data Index: 339531 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.3056. Min Act: -0.0000

Data Index: 1258808 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1367140 (Python Code)

Max Activating Token Index: 785

Text #14

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.3064. Min Act: -0.0000

Data Index: 1322723 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.2908. Min Act: -0.0000

Data Index: 548143 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.2901. Min Act: -0.0000

Data Index: 348205 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.2722. Min Act: -0.0000

Data Index: 801626 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1409165 (Python Code)

Max Activating Token Index: 448

Text #19

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1030500 (C4 (Web Text))

Max Activating Token Index: 334