Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2549 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6924. Min Act: -0.0001

Data Index: 1607747 (Python Code)

Max Activating Token Index: 831

Text #1

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6974. Min Act: -0.0001

Data Index: 1424485 (Python Code)

Max Activating Token Index: 814

Text #2

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6259. Min Act: -0.0001

Data Index: 1485867 (Python Code)

Max Activating Token Index: 833

Text #3

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6830. Min Act: -0.0001

Data Index: 1630289 (Python Code)

Max Activating Token Index: 264

Text #4

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5329. Min Act: -0.0001

Data Index: 1626265 (Python Code)

Max Activating Token Index: 722

Text #5

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6195. Min Act: -0.0001

Data Index: 1378303 (Python Code)

Max Activating Token Index: 644

Text #6

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6261. Min Act: -0.0001

Data Index: 1638203 (Python Code)

Max Activating Token Index: 726

Text #7

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6481. Min Act: -0.0001

Data Index: 1548383 (Python Code)

Max Activating Token Index: 128

Text #8

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5471. Min Act: -0.0001

Data Index: 1616279 (Python Code)

Max Activating Token Index: 754

Text #9

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5630. Min Act: -0.0001

Data Index: 1514404 (Python Code)

Max Activating Token Index: 528

Text #10

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5386. Min Act: -0.0001

Data Index: 1478474 (Python Code)

Max Activating Token Index: 985

Text #11

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5752. Min Act: -0.0001

Data Index: 1419557 (Python Code)

Max Activating Token Index: 113

Text #12

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5721. Min Act: -0.0001

Data Index: 1513036 (Python Code)

Max Activating Token Index: 989

Text #13

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5649. Min Act: -0.0001

Data Index: 1556593 (Python Code)

Max Activating Token Index: 360

Text #14

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5231. Min Act: -0.0001

Data Index: 1645765 (Python Code)

Max Activating Token Index: 214

Text #15

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5293. Min Act: -0.0001

Data Index: 1407934 (Python Code)

Max Activating Token Index: 947

Text #16

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5864. Min Act: -0.0001

Data Index: 1536143 (Python Code)

Max Activating Token Index: 770

Text #17

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5229. Min Act: -0.0001

Data Index: 1628256 (Python Code)

Max Activating Token Index: 924

Text #18

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5247. Min Act: -0.0001

Data Index: 1449897 (Python Code)

Max Activating Token Index: 706

Text #19

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5565. Min Act: -0.0001

Data Index: 1491841 (Python Code)

Max Activating Token Index: 878