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

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

Neuron 1054 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: 0.4590. Min Range: -0.4590

Max Act: 0.4565. Min Act: -0.0000

Data Index: 1375849 (Python Code)

Max Activating Token Index: 435

Text #1

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1514765 (Python Code)

Max Activating Token Index: 142

Text #2

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4590. Min Act: -0.0000

Data Index: 1555707 (Python Code)

Max Activating Token Index: 215

Text #3

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1450590 (Python Code)

Max Activating Token Index: 500

Text #4

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4181. Min Act: -0.0000

Data Index: 336872 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4341. Min Act: -0.0000

Data Index: 1512423 (Python Code)

Max Activating Token Index: 231

Text #6

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3900. Min Act: -0.0000

Data Index: 1506718 (Python Code)

Max Activating Token Index: 412

Text #7

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3788. Min Act: -0.0000

Data Index: 1565329 (Python Code)

Max Activating Token Index: 127

Text #8

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1568355 (Python Code)

Max Activating Token Index: 538

Text #9

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3811. Min Act: -0.0000

Data Index: 1537436 (Python Code)

Max Activating Token Index: 556

Text #10

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3434. Min Act: -0.0000

Data Index: 1617575 (Python Code)

Max Activating Token Index: 867

Text #11

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1020242 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3506. Min Act: -0.0000

Data Index: 1545220 (Python Code)

Max Activating Token Index: 886

Text #13

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3275. Min Act: -0.0000

Data Index: 1404627 (Python Code)

Max Activating Token Index: 86

Text #14

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3471. Min Act: -0.0000

Data Index: 1617593 (Python Code)

Max Activating Token Index: 770

Text #15

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3328. Min Act: -0.0000

Data Index: 1373660 (Python Code)

Max Activating Token Index: 87

Text #16

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3180. Min Act: -0.0000

Data Index: 1622393 (Python Code)

Max Activating Token Index: 149

Text #17

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1408561 (Python Code)

Max Activating Token Index: 269

Text #18

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3125. Min Act: -0.0000

Data Index: 1515030 (Python Code)

Max Activating Token Index: 368

Text #19

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1521094 (Python Code)

Max Activating Token Index: 91