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

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

Neuron 286 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: 1.0389. Min Range: -1.0389

Max Act: 1.0389. Min Act: -0.0001

Data Index: 1555560 (Python Code)

Max Activating Token Index: 893

Text #1

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9390. Min Act: -0.0001

Data Index: 1560696 (Python Code)

Max Activating Token Index: 185

Text #2

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8963. Min Act: -0.0001

Data Index: 1642358 (Python Code)

Max Activating Token Index: 120

Text #3

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9070. Min Act: -0.0001

Data Index: 1586619 (Python Code)

Max Activating Token Index: 633

Text #4

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9178. Min Act: -0.0001

Data Index: 1471805 (Python Code)

Max Activating Token Index: 583

Text #5

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9083. Min Act: -0.0001

Data Index: 1430199 (Python Code)

Max Activating Token Index: 173

Text #6

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8485. Min Act: -0.0001

Data Index: 1516525 (Python Code)

Max Activating Token Index: 198

Text #7

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8390. Min Act: -0.0001

Data Index: 1552982 (Python Code)

Max Activating Token Index: 881

Text #8

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8045. Min Act: -0.0001

Data Index: 1373564 (Python Code)

Max Activating Token Index: 719

Text #9

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8314. Min Act: -0.0001

Data Index: 1519047 (Python Code)

Max Activating Token Index: 206

Text #10

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7728. Min Act: -0.0001

Data Index: 1586767 (Python Code)

Max Activating Token Index: 511

Text #11

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7652. Min Act: -0.0001

Data Index: 1564264 (Python Code)

Max Activating Token Index: 897

Text #12

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8159. Min Act: -0.0001

Data Index: 1628131 (Python Code)

Max Activating Token Index: 380

Text #13

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7264. Min Act: -0.0001

Data Index: 1397435 (Python Code)

Max Activating Token Index: 884

Text #14

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8273. Min Act: -0.0001

Data Index: 1579448 (Python Code)

Max Activating Token Index: 340

Text #15

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7365. Min Act: -0.0001

Data Index: 1616152 (Python Code)

Max Activating Token Index: 601

Text #16

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7325. Min Act: -0.0001

Data Index: 1459997 (Python Code)

Max Activating Token Index: 884

Text #17

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7321. Min Act: -0.0001

Data Index: 1451037 (Python Code)

Max Activating Token Index: 1016

Text #18

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7752. Min Act: -0.0001

Data Index: 1458979 (Python Code)

Max Activating Token Index: 1021

Text #19

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7624. Min Act: -0.0001

Data Index: 1654609 (Python Code)

Max Activating Token Index: 552