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

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

Neuron 5119 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0477. Min Act: -0.0001

Data Index: 921439 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1317585 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0487. Min Act: -0.0001

Data Index: 561162 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0491. Min Act: -0.0001

Data Index: 1614094 (Python Code)

Max Activating Token Index: 99

Text #4

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0492. Min Act: -0.0001

Data Index: 1087514 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0463. Min Act: -0.0001

Data Index: 126438 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0441. Min Act: -0.0001

Data Index: 981685 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0438. Min Act: -0.0001

Data Index: 815298 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0484. Min Act: -0.0001

Data Index: 111823 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0432. Min Act: -0.0001

Data Index: 1559477 (Python Code)

Max Activating Token Index: 431

Text #10

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0463. Min Act: -0.0001

Data Index: 127449 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0437. Min Act: -0.0001

Data Index: 1054871 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0430. Min Act: -0.0001

Data Index: 35296 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0387. Min Act: -0.0001

Data Index: 1290787 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0382. Min Act: -0.0001

Data Index: 1309094 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1641639 (Python Code)

Max Activating Token Index: 941

Text #16

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0374. Min Act: -0.0001

Data Index: 937791 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0406. Min Act: -0.0001

Data Index: 680850 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0338. Min Act: -0.0001

Data Index: 544410 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0405. Min Act: -0.0001

Data Index: 481622 (C4 (Web Text))

Max Activating Token Index: 125