Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 170 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0580. Min Act: -0.0001

Data Index: 486811 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0556. Min Act: -0.0001

Data Index: 663908 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1255173 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0500. Min Act: -0.0001

Data Index: 634739 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0504. Min Act: -0.0001

Data Index: 945775 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0494. Min Act: -0.0001

Data Index: 1078807 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1104181 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0491. Min Act: -0.0001

Data Index: 365787 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0488. Min Act: -0.0001

Data Index: 1084765 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0481. Min Act: -0.0001

Data Index: 140601 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0453. Min Act: -0.0001

Data Index: 200740 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1356940 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0484. Min Act: -0.0001

Data Index: 832159 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0448. Min Act: -0.0001

Data Index: 810705 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0464. Min Act: -0.0001

Data Index: 466130 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0480. Min Act: -0.0001

Data Index: 1111872 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0447. Min Act: -0.0001

Data Index: 980643 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0459. Min Act: -0.0001

Data Index: 908882 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0439. Min Act: -0.0001

Data Index: 465286 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0428. Min Act: -0.0001

Data Index: 833854 (C4 (Web Text))

Max Activating Token Index: 606