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

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

Neuron 5686 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0073. Min Range: -4.0073

Max Act: 4.0073. Min Act: -0.0000

Data Index: 1435996 (Python Code)

Max Activating Token Index: 161

Text #1

Max Range: 4.0073. Min Range: -4.0073

Max Act: 3.3611. Min Act: -0.0000

Data Index: 1389768 (Python Code)

Max Activating Token Index: 874

Text #2

Max Range: 4.0073. Min Range: -4.0073

Max Act: 3.2216. Min Act: -0.0000

Data Index: 868025 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 4.0073. Min Range: -4.0073

Max Act: 2.5881. Min Act: -0.0000

Data Index: 290526 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 4.0073. Min Range: -4.0073

Max Act: 3.0654. Min Act: -0.0000

Data Index: 670350 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 4.0073. Min Range: -4.0073

Max Act: 2.9360. Min Act: -0.0000

Data Index: 846208 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 4.0073. Min Range: -4.0073

Max Act: 3.0186. Min Act: -0.0000

Data Index: 1324288 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 4.0073. Min Range: -4.0073

Max Act: 2.6421. Min Act: -0.0000

Data Index: 1268810 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 4.0073. Min Range: -4.0073

Max Act: 2.8584. Min Act: -0.0000

Data Index: 396449 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 4.0073. Min Range: -4.0073

Max Act: 2.3385. Min Act: -0.0000

Data Index: 967803 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 4.0073. Min Range: -4.0073

Max Act: 2.5138. Min Act: -0.0000

Data Index: 1281864 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 4.0073. Min Range: -4.0073

Max Act: 2.4756. Min Act: -0.0000

Data Index: 127738 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 4.0073. Min Range: -4.0073

Max Act: 2.8469. Min Act: -0.0000

Data Index: 1516060 (Python Code)

Max Activating Token Index: 1001

Text #13

Max Range: 4.0073. Min Range: -4.0073

Max Act: 2.5649. Min Act: -0.0000

Data Index: 1572742 (Python Code)

Max Activating Token Index: 162

Text #14

Max Range: 4.0073. Min Range: -4.0073

Max Act: 2.2991. Min Act: -0.0000

Data Index: 672118 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 4.0073. Min Range: -4.0073

Max Act: 2.1768. Min Act: -0.0000

Data Index: 387650 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 4.0073. Min Range: -4.0073

Max Act: 2.5395. Min Act: -0.0000

Data Index: 1539212 (Python Code)

Max Activating Token Index: 565

Text #17

Max Range: 4.0073. Min Range: -4.0073

Max Act: 2.5291. Min Act: -0.0000

Data Index: 217963 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 4.0073. Min Range: -4.0073

Max Act: 2.6185. Min Act: -0.0000

Data Index: 309049 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 4.0073. Min Range: -4.0073

Max Act: 2.4911. Min Act: -0.0000

Data Index: 1548206 (Python Code)

Max Activating Token Index: 371