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

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

Neuron 4074 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0685. Min Range: -1.0685

Max Act: 1.0172. Min Act: -0.0001

Data Index: 1029600 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 1.0685. Min Range: -1.0685

Max Act: 1.0685. Min Act: -0.0001

Data Index: 1618680 (Python Code)

Max Activating Token Index: 26

Text #2

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.8790. Min Act: -0.0001

Data Index: 1476429 (Python Code)

Max Activating Token Index: 632

Text #3

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9327. Min Act: -0.0001

Data Index: 1448591 (Python Code)

Max Activating Token Index: 712

Text #4

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9327. Min Act: -0.0001

Data Index: 1442549 (Python Code)

Max Activating Token Index: 848

Text #5

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9111. Min Act: -0.0001

Data Index: 724447 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9392. Min Act: -0.0001

Data Index: 1554381 (Python Code)

Max Activating Token Index: 557

Text #7

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.8517. Min Act: -0.0001

Data Index: 677718 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9461. Min Act: -0.0001

Data Index: 859387 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.8505. Min Act: -0.0001

Data Index: 1601918 (Python Code)

Max Activating Token Index: 858

Text #10

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9463. Min Act: -0.0001

Data Index: 1496912 (Python Code)

Max Activating Token Index: 197

Text #11

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.8651. Min Act: -0.0001

Data Index: 1594466 (Python Code)

Max Activating Token Index: 885

Text #12

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9123. Min Act: -0.0001

Data Index: 1587028 (Python Code)

Max Activating Token Index: 462

Text #13

Max Range: 1.0685. Min Range: -1.0685

Max Act: 1.0245. Min Act: -0.0001

Data Index: 1645893 (Python Code)

Max Activating Token Index: 703

Text #14

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.8321. Min Act: -0.0001

Data Index: 1463328 (Python Code)

Max Activating Token Index: 537

Text #15

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.8814. Min Act: -0.0001

Data Index: 1541694 (Python Code)

Max Activating Token Index: 515

Text #16

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9086. Min Act: -0.0001

Data Index: 767473 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.8283. Min Act: -0.0001

Data Index: 1558647 (Python Code)

Max Activating Token Index: 912

Text #18

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9344. Min Act: -0.0001

Data Index: 1427590 (Python Code)

Max Activating Token Index: 798

Text #19

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9343. Min Act: -0.0001

Data Index: 1625087 (Python Code)

Max Activating Token Index: 330