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

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

Neuron 2237 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.8099. Min Act: -0.0001

Data Index: 1459797 (Python Code)

Max Activating Token Index: 242

Text #1

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.7792. Min Act: -0.0001

Data Index: 1538756 (Python Code)

Max Activating Token Index: 160

Text #2

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.7401. Min Act: -0.0001

Data Index: 1491368 (Python Code)

Max Activating Token Index: 19

Text #3

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6910. Min Act: -0.0001

Data Index: 1553023 (Python Code)

Max Activating Token Index: 1007

Text #4

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6352. Min Act: -0.0001

Data Index: 1434484 (Python Code)

Max Activating Token Index: 929

Text #5

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6100. Min Act: -0.0001

Data Index: 1403714 (Python Code)

Max Activating Token Index: 576

Text #6

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6222. Min Act: -0.0001

Data Index: 1603364 (Python Code)

Max Activating Token Index: 58

Text #7

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6176. Min Act: -0.0001

Data Index: 1512820 (Python Code)

Max Activating Token Index: 432

Text #8

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5789. Min Act: -0.0001

Data Index: 1647888 (Python Code)

Max Activating Token Index: 447

Text #9

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6097. Min Act: -0.0001

Data Index: 1382214 (Python Code)

Max Activating Token Index: 743

Text #10

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5847. Min Act: -0.0001

Data Index: 1555193 (Python Code)

Max Activating Token Index: 21

Text #11

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5860. Min Act: -0.0001

Data Index: 1479101 (Python Code)

Max Activating Token Index: 620

Text #12

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6018. Min Act: -0.0001

Data Index: 1389312 (Python Code)

Max Activating Token Index: 671

Text #13

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5621. Min Act: -0.0001

Data Index: 1467381 (Python Code)

Max Activating Token Index: 292

Text #14

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5795. Min Act: -0.0001

Data Index: 1600284 (Python Code)

Max Activating Token Index: 720

Text #15

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5937. Min Act: -0.0001

Data Index: 1370875 (Python Code)

Max Activating Token Index: 628

Text #16

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5815. Min Act: -0.0001

Data Index: 1428300 (Python Code)

Max Activating Token Index: 997

Text #17

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5882. Min Act: -0.0001

Data Index: 1474587 (Python Code)

Max Activating Token Index: 653

Text #18

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6068. Min Act: -0.0001

Data Index: 1370882 (Python Code)

Max Activating Token Index: 187

Text #19

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5429. Min Act: -0.0001

Data Index: 1533682 (Python Code)

Max Activating Token Index: 146