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

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

Neuron 5023 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3358. Min Range: -2.3358

Max Act: 2.3358. Min Act: -0.0000

Data Index: 1641935 (Python Code)

Max Activating Token Index: 891

Text #1

Max Range: 2.3358. Min Range: -2.3358

Max Act: 1.3206. Min Act: -0.0000

Data Index: 1593126 (Python Code)

Max Activating Token Index: 368

Text #2

Max Range: 2.3358. Min Range: -2.3358

Max Act: 1.2038. Min Act: -0.0000

Data Index: 1371604 (Python Code)

Max Activating Token Index: 724

Text #3

Max Range: 2.3358. Min Range: -2.3358

Max Act: 1.1946. Min Act: -0.0000

Data Index: 1564520 (Python Code)

Max Activating Token Index: 285

Text #4

Max Range: 2.3358. Min Range: -2.3358

Max Act: 1.2278. Min Act: -0.0000

Data Index: 1510604 (Python Code)

Max Activating Token Index: 273

Text #5

Max Range: 2.3358. Min Range: -2.3358

Max Act: 1.1962. Min Act: -0.0000

Data Index: 1636500 (Python Code)

Max Activating Token Index: 158

Text #6

Max Range: 2.3358. Min Range: -2.3358

Max Act: 1.1524. Min Act: -0.0000

Data Index: 1489124 (Python Code)

Max Activating Token Index: 825

Text #7

Max Range: 2.3358. Min Range: -2.3358

Max Act: 1.0714. Min Act: -0.0000

Data Index: 454800 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 2.3358. Min Range: -2.3358

Max Act: 1.0627. Min Act: -0.0000

Data Index: 1020665 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 2.3358. Min Range: -2.3358

Max Act: 1.0270. Min Act: -0.0000

Data Index: 1133172 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 2.3358. Min Range: -2.3358

Max Act: 1.0851. Min Act: -0.0000

Data Index: 1506103 (Python Code)

Max Activating Token Index: 469

Text #11

Max Range: 2.3358. Min Range: -2.3358

Max Act: 1.0417. Min Act: -0.0000

Data Index: 1094180 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 2.3358. Min Range: -2.3358

Max Act: 0.9838. Min Act: 0.0000

Data Index: 1487489 (Python Code)

Max Activating Token Index: 169

Text #13

Max Range: 2.3358. Min Range: -2.3358

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1648328 (Python Code)

Max Activating Token Index: 33

Text #14

Max Range: 2.3358. Min Range: -2.3358

Max Act: 1.0665. Min Act: -0.0000

Data Index: 320379 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 2.3358. Min Range: -2.3358

Max Act: 0.9964. Min Act: -0.0000

Data Index: 1574385 (Python Code)

Max Activating Token Index: 102

Text #16

Max Range: 2.3358. Min Range: -2.3358

Max Act: 1.0227. Min Act: -0.0000

Data Index: 486470 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 2.3358. Min Range: -2.3358

Max Act: 0.9590. Min Act: 0.0000

Data Index: 1565936 (Python Code)

Max Activating Token Index: 252

Text #18

Max Range: 2.3358. Min Range: -2.3358

Max Act: 0.9651. Min Act: -0.0000

Data Index: 221499 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 2.3358. Min Range: -2.3358

Max Act: 0.9832. Min Act: -0.0000

Data Index: 1566608 (Python Code)

Max Activating Token Index: 302