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

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

Neuron 4634 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8359. Min Act: -0.0000

Data Index: 1126363 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8540. Min Act: 0.0001

Data Index: 167141 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7778. Min Act: -0.0000

Data Index: 792781 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7527. Min Act: -0.0000

Data Index: 527522 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7974. Min Act: 0.0000

Data Index: 361853 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7367. Min Act: -0.0000

Data Index: 890220 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7268. Min Act: 0.0000

Data Index: 391696 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7599. Min Act: 0.0001

Data Index: 1236076 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7323. Min Act: -0.0000

Data Index: 91984 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7233. Min Act: 0.0001

Data Index: 1179924 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7160. Min Act: 0.0001

Data Index: 28138 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7178. Min Act: -0.0000

Data Index: 231942 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6867. Min Act: -0.0000

Data Index: 395331 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1352326 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6354. Min Act: 0.0000

Data Index: 607763 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6534. Min Act: 0.0000

Data Index: 747389 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6206. Min Act: 0.0001

Data Index: 295235 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6444. Min Act: 0.0000

Data Index: 13709 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6431. Min Act: 0.0001

Data Index: 589868 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1098797 (C4 (Web Text))

Max Activating Token Index: 684