Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4129 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.4711. Min Range: -4.4711

Max Act: 4.4711. Min Act: -0.0000

Data Index: 1459713 (Python Code)

Max Activating Token Index: 740

Text #1

Max Range: 4.4711. Min Range: -4.4711

Max Act: 4.2967. Min Act: -0.0000

Data Index: 1394413 (Python Code)

Max Activating Token Index: 520

Text #2

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.7750. Min Act: -0.0000

Data Index: 1488313 (Python Code)

Max Activating Token Index: 708

Text #3

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.4805. Min Act: -0.0000

Data Index: 1515208 (Python Code)

Max Activating Token Index: 557

Text #4

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.6426. Min Act: -0.0000

Data Index: 1595085 (Python Code)

Max Activating Token Index: 512

Text #5

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.4532. Min Act: -0.0000

Data Index: 1456916 (Python Code)

Max Activating Token Index: 401

Text #6

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.2269. Min Act: -0.0000

Data Index: 1585544 (Python Code)

Max Activating Token Index: 901

Text #7

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.5272. Min Act: -0.0000

Data Index: 1519843 (Python Code)

Max Activating Token Index: 809

Text #8

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.6738. Min Act: -0.0000

Data Index: 1614283 (Python Code)

Max Activating Token Index: 642

Text #9

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.5959. Min Act: -0.0000

Data Index: 1544264 (Python Code)

Max Activating Token Index: 958

Text #10

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.3611. Min Act: -0.0000

Data Index: 1547027 (Python Code)

Max Activating Token Index: 130

Text #11

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.3349. Min Act: -0.0000

Data Index: 1414718 (Python Code)

Max Activating Token Index: 187

Text #12

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.3665. Min Act: -0.0000

Data Index: 1613284 (Python Code)

Max Activating Token Index: 364

Text #13

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.4972. Min Act: -0.0000

Data Index: 1489162 (Python Code)

Max Activating Token Index: 528

Text #14

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.4876. Min Act: -0.0000

Data Index: 1537916 (Python Code)

Max Activating Token Index: 429

Text #15

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.1834. Min Act: -0.0000

Data Index: 1384683 (Python Code)

Max Activating Token Index: 604

Text #16

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.4533. Min Act: -0.0000

Data Index: 1374419 (Python Code)

Max Activating Token Index: 768

Text #17

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.4495. Min Act: -0.0000

Data Index: 1539541 (Python Code)

Max Activating Token Index: 341

Text #18

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.2995. Min Act: -0.0000

Data Index: 1570334 (Python Code)

Max Activating Token Index: 173

Text #19

Max Range: 4.4711. Min Range: -4.4711

Max Act: 3.3981. Min Act: -0.0000

Data Index: 1482962 (Python Code)

Max Activating Token Index: 820