Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3239 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.4560. Min Act: -0.0001

Data Index: 1381257 (Python Code)

Max Activating Token Index: 886

Text #1

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.4031. Min Act: -0.0001

Data Index: 1614976 (Python Code)

Max Activating Token Index: 10

Text #2

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.4509. Min Act: -0.0001

Data Index: 1401446 (Python Code)

Max Activating Token Index: 64

Text #3

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3928. Min Act: -0.0001

Data Index: 1498576 (Python Code)

Max Activating Token Index: 54

Text #4

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3537. Min Act: -0.0001

Data Index: 1373317 (Python Code)

Max Activating Token Index: 16

Text #5

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3623. Min Act: -0.0001

Data Index: 1378471 (Python Code)

Max Activating Token Index: 204

Text #6

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3615. Min Act: -0.0001

Data Index: 1636339 (Python Code)

Max Activating Token Index: 163

Text #7

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3570. Min Act: -0.0001

Data Index: 1595849 (Python Code)

Max Activating Token Index: 510

Text #8

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3401. Min Act: -0.0001

Data Index: 1426606 (Python Code)

Max Activating Token Index: 45

Text #9

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3609. Min Act: -0.0001

Data Index: 1541463 (Python Code)

Max Activating Token Index: 744

Text #10

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.2998. Min Act: -0.0001

Data Index: 1639085 (Python Code)

Max Activating Token Index: 722

Text #11

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3352. Min Act: -0.0001

Data Index: 1577428 (Python Code)

Max Activating Token Index: 647

Text #12

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3328. Min Act: -0.0001

Data Index: 1535177 (Python Code)

Max Activating Token Index: 927

Text #13

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3326. Min Act: -0.0001

Data Index: 1419741 (Python Code)

Max Activating Token Index: 24

Text #14

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3076. Min Act: -0.0001

Data Index: 1485926 (Python Code)

Max Activating Token Index: 84

Text #15

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3167. Min Act: -0.0001

Data Index: 1579159 (Python Code)

Max Activating Token Index: 9

Text #16

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3167. Min Act: -0.0001

Data Index: 1487140 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3149. Min Act: -0.0001

Data Index: 1370433 (Python Code)

Max Activating Token Index: 223

Text #18

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3139. Min Act: -0.0001

Data Index: 1391969 (Python Code)

Max Activating Token Index: 133

Text #19

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3353. Min Act: -0.0001

Data Index: 1604082 (Python Code)

Max Activating Token Index: 420