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

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

Neuron 4470 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.9747. Min Act: -0.0000

Data Index: 1540539 (Python Code)

Max Activating Token Index: 951

Text #1

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.7855. Min Act: -0.0000

Data Index: 1541351 (Python Code)

Max Activating Token Index: 219

Text #2

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.4334. Min Act: -0.0000

Data Index: 1371404 (Python Code)

Max Activating Token Index: 980

Text #3

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.7003. Min Act: -0.0000

Data Index: 1408149 (Python Code)

Max Activating Token Index: 708

Text #4

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.6715. Min Act: -0.0000

Data Index: 1638594 (Python Code)

Max Activating Token Index: 800

Text #5

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.5855. Min Act: -0.0000

Data Index: 1604982 (Python Code)

Max Activating Token Index: 382

Text #6

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.4327. Min Act: -0.0000

Data Index: 1618802 (Python Code)

Max Activating Token Index: 304

Text #7

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.4555. Min Act: -0.0000

Data Index: 1487002 (Python Code)

Max Activating Token Index: 281

Text #8

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.4497. Min Act: -0.0000

Data Index: 1543736 (Python Code)

Max Activating Token Index: 521

Text #9

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.4378. Min Act: -0.0000

Data Index: 1372115 (Python Code)

Max Activating Token Index: 749

Text #10

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.3260. Min Act: -0.0000

Data Index: 1516002 (Python Code)

Max Activating Token Index: 578

Text #11

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.4334. Min Act: -0.0000

Data Index: 1645929 (Python Code)

Max Activating Token Index: 656

Text #12

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.3459. Min Act: -0.0000

Data Index: 1536359 (Python Code)

Max Activating Token Index: 599

Text #13

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.4499. Min Act: -0.0000

Data Index: 1548447 (Python Code)

Max Activating Token Index: 681

Text #14

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.3209. Min Act: -0.0000

Data Index: 1363075 (Python Code)

Max Activating Token Index: 482

Text #15

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.4346. Min Act: -0.0000

Data Index: 1517002 (Python Code)

Max Activating Token Index: 685

Text #16

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.2652. Min Act: -0.0000

Data Index: 1650160 (Python Code)

Max Activating Token Index: 842

Text #17

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.3781. Min Act: -0.0000

Data Index: 1493734 (Python Code)

Max Activating Token Index: 490

Text #18

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.3789. Min Act: -0.0000

Data Index: 1441130 (Python Code)

Max Activating Token Index: 810

Text #19

Max Range: 2.9747. Min Range: -2.9747

Max Act: 2.3946. Min Act: -0.0000

Data Index: 1496466 (Python Code)

Max Activating Token Index: 759