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

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

Neuron 1133 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: 0.9783. Min Range: -0.9783

Max Act: 0.9783. Min Act: -0.0000

Data Index: 1398564 (Python Code)

Max Activating Token Index: 538

Text #1

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.8507. Min Act: -0.0000

Data Index: 1385339 (Python Code)

Max Activating Token Index: 406

Text #2

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1494402 (Python Code)

Max Activating Token Index: 647

Text #3

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.8026. Min Act: -0.0000

Data Index: 1594999 (Python Code)

Max Activating Token Index: 888

Text #4

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1393222 (Python Code)

Max Activating Token Index: 164

Text #5

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.7390. Min Act: -0.0000

Data Index: 1458043 (Python Code)

Max Activating Token Index: 634

Text #6

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6859. Min Act: -0.0000

Data Index: 1569804 (Python Code)

Max Activating Token Index: 537

Text #7

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1431593 (Python Code)

Max Activating Token Index: 475

Text #8

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.7251. Min Act: -0.0000

Data Index: 1580295 (Python Code)

Max Activating Token Index: 452

Text #9

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.7365. Min Act: -0.0000

Data Index: 1448996 (Python Code)

Max Activating Token Index: 781

Text #10

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.7165. Min Act: -0.0000

Data Index: 1555485 (Python Code)

Max Activating Token Index: 297

Text #11

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1537402 (Python Code)

Max Activating Token Index: 517

Text #12

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1531339 (Python Code)

Max Activating Token Index: 649

Text #13

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1376962 (Python Code)

Max Activating Token Index: 159

Text #14

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.5983. Min Act: -0.0000

Data Index: 1436552 (Python Code)

Max Activating Token Index: 271

Text #15

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1382390 (Python Code)

Max Activating Token Index: 177

Text #16

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6277. Min Act: -0.0000

Data Index: 1375632 (Python Code)

Max Activating Token Index: 330

Text #17

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6086. Min Act: -0.0000

Data Index: 1399083 (Python Code)

Max Activating Token Index: 1019

Text #18

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1495981 (Python Code)

Max Activating Token Index: 256

Text #19

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.5832. Min Act: -0.0001

Data Index: 1461045 (Python Code)

Max Activating Token Index: 824