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

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

Neuron 874 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.7736. Min Act: -0.0000

Data Index: 1445724 (Python Code)

Max Activating Token Index: 67

Text #1

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.4463. Min Act: -0.0000

Data Index: 1520389 (Python Code)

Max Activating Token Index: 820

Text #2

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1395368 (Python Code)

Max Activating Token Index: 493

Text #3

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.4460. Min Act: -0.0000

Data Index: 1362398 (Python Code)

Max Activating Token Index: 949

Text #4

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.4759. Min Act: -0.0000

Data Index: 1422428 (Python Code)

Max Activating Token Index: 238

Text #5

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.4726. Min Act: -0.0000

Data Index: 1594771 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.3703. Min Act: -0.0000

Data Index: 1392960 (Python Code)

Max Activating Token Index: 710

Text #7

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.5510. Min Act: -0.0000

Data Index: 1403211 (Python Code)

Max Activating Token Index: 52

Text #8

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.4288. Min Act: -0.0000

Data Index: 303299 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.4209. Min Act: -0.0000

Data Index: 1511356 (Python Code)

Max Activating Token Index: 802

Text #10

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.3980. Min Act: -0.0000

Data Index: 1426881 (Python Code)

Max Activating Token Index: 467

Text #11

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.3938. Min Act: -0.0000

Data Index: 1364114 (Python Code)

Max Activating Token Index: 403

Text #12

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.4007. Min Act: -0.0000

Data Index: 477827 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.4038. Min Act: -0.0000

Data Index: 526322 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.3881. Min Act: -0.0000

Data Index: 1529431 (Python Code)

Max Activating Token Index: 408

Text #15

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.4458. Min Act: -0.0000

Data Index: 1493616 (Python Code)

Max Activating Token Index: 457

Text #16

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.4354. Min Act: -0.0000

Data Index: 1444666 (Python Code)

Max Activating Token Index: 949

Text #17

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.2571. Min Act: -0.0000

Data Index: 1442147 (Python Code)

Max Activating Token Index: 272

Text #18

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.2440. Min Act: -0.0000

Data Index: 1092920 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 1.7736. Min Range: -1.7736

Max Act: 1.3109. Min Act: -0.0000

Data Index: 1534695 (Python Code)

Max Activating Token Index: 24