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

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

Neuron 3869 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0340. Min Range: -3.0340

Max Act: 3.0340. Min Act: -0.0001

Data Index: 1421825 (Python Code)

Max Activating Token Index: 45

Text #1

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.7825. Min Act: -0.0001

Data Index: 1615477 (Python Code)

Max Activating Token Index: 82

Text #2

Max Range: 3.0340. Min Range: -3.0340

Max Act: 3.0047. Min Act: -0.0001

Data Index: 1363853 (Python Code)

Max Activating Token Index: 42

Text #3

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.8044. Min Act: -0.0001

Data Index: 1626864 (Python Code)

Max Activating Token Index: 575

Text #4

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.7774. Min Act: -0.0001

Data Index: 1556458 (Python Code)

Max Activating Token Index: 11

Text #5

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.8739. Min Act: -0.0001

Data Index: 1639762 (Python Code)

Max Activating Token Index: 329

Text #6

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.7327. Min Act: -0.0001

Data Index: 1382817 (Python Code)

Max Activating Token Index: 155

Text #7

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.5830. Min Act: -0.0001

Data Index: 1420417 (Python Code)

Max Activating Token Index: 646

Text #8

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.6783. Min Act: -0.0001

Data Index: 1365360 (Python Code)

Max Activating Token Index: 255

Text #9

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.6650. Min Act: -0.0001

Data Index: 1543153 (Python Code)

Max Activating Token Index: 528

Text #10

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.5486. Min Act: -0.0001

Data Index: 1459961 (Python Code)

Max Activating Token Index: 945

Text #11

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.6259. Min Act: -0.0001

Data Index: 1379456 (Python Code)

Max Activating Token Index: 565

Text #12

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.4769. Min Act: -0.0001

Data Index: 1592227 (Python Code)

Max Activating Token Index: 182

Text #13

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.5739. Min Act: -0.0001

Data Index: 1413604 (Python Code)

Max Activating Token Index: 483

Text #14

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.5562. Min Act: -0.0001

Data Index: 1622000 (Python Code)

Max Activating Token Index: 456

Text #15

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.5659. Min Act: -0.0001

Data Index: 1612352 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.5396. Min Act: -0.0001

Data Index: 1444203 (Python Code)

Max Activating Token Index: 182

Text #17

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.5443. Min Act: -0.0001

Data Index: 1599844 (Python Code)

Max Activating Token Index: 338

Text #18

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.3054. Min Act: -0.0001

Data Index: 1656657 (Python Code)

Max Activating Token Index: 530

Text #19

Max Range: 3.0340. Min Range: -3.0340

Max Act: 2.5081. Min Act: -0.0001

Data Index: 1370220 (Python Code)

Max Activating Token Index: 53