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

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

Neuron 768 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.9674. Min Act: -0.0000

Data Index: 743496 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.9575. Min Act: -0.0000

Data Index: 841778 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1140405 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1225388 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.7655. Min Act: -0.0000

Data Index: 180660 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.7150. Min Act: -0.0000

Data Index: 708211 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.7523. Min Act: -0.0000

Data Index: 927670 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.6563. Min Act: -0.0000

Data Index: 773408 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.6530. Min Act: -0.0000

Data Index: 619041 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.6264. Min Act: -0.0000

Data Index: 52248 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.6030. Min Act: -0.0000

Data Index: 80862 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.6397. Min Act: -0.0000

Data Index: 1022756 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.6311. Min Act: -0.0000

Data Index: 289101 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1007698 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.6098. Min Act: -0.0000

Data Index: 984743 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1107791 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.6192. Min Act: -0.0000

Data Index: 1298515 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.5969. Min Act: -0.0000

Data Index: 158796 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.5804. Min Act: -0.0000

Data Index: 1306928 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.9674. Min Range: -0.9674

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1064295 (C4 (Web Text))

Max Activating Token Index: 714