Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2459 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0802. Min Range: -1.0802

Max Act: 1.0563. Min Act: -0.0000

Data Index: 1461688 (Python Code)

Max Activating Token Index: 149

Text #1

Max Range: 1.0802. Min Range: -1.0802

Max Act: 1.0802. Min Act: -0.0000

Data Index: 1378156 (Python Code)

Max Activating Token Index: 260

Text #2

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9949. Min Act: -0.0000

Data Index: 1520083 (Python Code)

Max Activating Token Index: 265

Text #3

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9213. Min Act: -0.0000

Data Index: 1416460 (Python Code)

Max Activating Token Index: 919

Text #4

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8646. Min Act: -0.0000

Data Index: 1373577 (Python Code)

Max Activating Token Index: 466

Text #5

Max Range: 1.0802. Min Range: -1.0802

Max Act: 1.0135. Min Act: -0.0000

Data Index: 1477352 (Python Code)

Max Activating Token Index: 120

Text #6

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9728. Min Act: -0.0000

Data Index: 1590569 (Python Code)

Max Activating Token Index: 907

Text #7

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9577. Min Act: -0.0000

Data Index: 1466007 (Python Code)

Max Activating Token Index: 956

Text #8

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1527278 (Python Code)

Max Activating Token Index: 461

Text #9

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8536. Min Act: -0.0000

Data Index: 1639554 (Python Code)

Max Activating Token Index: 421

Text #10

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8478. Min Act: -0.0000

Data Index: 1496391 (Python Code)

Max Activating Token Index: 124

Text #11

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8375. Min Act: -0.0000

Data Index: 1610181 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8436. Min Act: -0.0000

Data Index: 1565747 (Python Code)

Max Activating Token Index: 324

Text #13

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1574200 (Python Code)

Max Activating Token Index: 241

Text #14

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1504857 (Python Code)

Max Activating Token Index: 602

Text #15

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1514694 (Python Code)

Max Activating Token Index: 595

Text #16

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1431025 (Python Code)

Max Activating Token Index: 31

Text #17

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7471. Min Act: -0.0000

Data Index: 1474737 (Python Code)

Max Activating Token Index: 477

Text #18

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1423922 (Python Code)

Max Activating Token Index: 504

Text #19

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7913. Min Act: -0.0000

Data Index: 1483604 (Python Code)

Max Activating Token Index: 117