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

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

Neuron 1837 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1547. Min Range: -2.1547

Max Act: 2.1547. Min Act: -0.0000

Data Index: 1488373 (Python Code)

Max Activating Token Index: 434

Text #1

Max Range: 2.1547. Min Range: -2.1547

Max Act: 1.9621. Min Act: -0.0000

Data Index: 1394711 (Python Code)

Max Activating Token Index: 353

Text #2

Max Range: 2.1547. Min Range: -2.1547

Max Act: 1.9244. Min Act: -0.0000

Data Index: 1584536 (Python Code)

Max Activating Token Index: 69

Text #3

Max Range: 2.1547. Min Range: -2.1547

Max Act: 1.8599. Min Act: -0.0000

Data Index: 1533990 (Python Code)

Max Activating Token Index: 61

Text #4

Max Range: 2.1547. Min Range: -2.1547

Max Act: 1.7369. Min Act: -0.0000

Data Index: 1359902 (Python Code)

Max Activating Token Index: 465

Text #5

Max Range: 2.1547. Min Range: -2.1547

Max Act: 1.6625. Min Act: -0.0000

Data Index: 1492056 (Python Code)

Max Activating Token Index: 774

Text #6

Max Range: 2.1547. Min Range: -2.1547

Max Act: 1.8080. Min Act: -0.0000

Data Index: 1513459 (Python Code)

Max Activating Token Index: 614

Text #7

Max Range: 2.1547. Min Range: -2.1547

Max Act: 1.7340. Min Act: -0.0000

Data Index: 1398592 (Python Code)

Max Activating Token Index: 90

Text #8

Max Range: 2.1547. Min Range: -2.1547

Max Act: 1.5685. Min Act: -0.0000

Data Index: 1422040 (Python Code)

Max Activating Token Index: 216

Text #9

Max Range: 2.1547. Min Range: -2.1547

Max Act: 1.6635. Min Act: -0.0000

Data Index: 1627161 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 2.1547. Min Range: -2.1547

Max Act: 1.6385. Min Act: -0.0000

Data Index: 1636266 (Python Code)

Max Activating Token Index: 158

Text #11

Max Range: 2.1547. Min Range: -2.1547

Max Act: 1.6157. Min Act: -0.0000

Data Index: 1403367 (Python Code)

Max Activating Token Index: 640

Text #12

Max Range: 2.1547. Min Range: -2.1547

Max Act: 1.6048. Min Act: -0.0000

Data Index: 1492639 (Python Code)

Max Activating Token Index: 30

Text #13

Max Range: 2.1547. Min Range: -2.1547

Max Act: 1.5778. Min Act: -0.0000

Data Index: 1495747 (Python Code)

Max Activating Token Index: 293

Text #14

Max Range: 2.1547. Min Range: -2.1547

Max Act: 1.6089. Min Act: -0.0000

Data Index: 1477148 (Python Code)

Max Activating Token Index: 510

Text #15

Max Range: 2.1547. Min Range: -2.1547

Max Act: 1.5476. Min Act: -0.0000

Data Index: 1578877 (Python Code)

Max Activating Token Index: 294

Text #16

Max Range: 2.1547. Min Range: -2.1547

Max Act: 1.5505. Min Act: -0.0000

Data Index: 1492845 (Python Code)

Max Activating Token Index: 66

Text #17

Max Range: 2.1547. Min Range: -2.1547

Max Act: 1.5707. Min Act: -0.0000

Data Index: 1558508 (Python Code)

Max Activating Token Index: 161

Text #18

Max Range: 2.1547. Min Range: -2.1547

Max Act: 1.5333. Min Act: -0.0000

Data Index: 1488504 (Python Code)

Max Activating Token Index: 466

Text #19

Max Range: 2.1547. Min Range: -2.1547

Max Act: 1.4183. Min Act: -0.0000

Data Index: 1441707 (Python Code)

Max Activating Token Index: 75