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

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

Neuron 1642 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.7886. Min Act: -0.0000

Data Index: 1574594 (Python Code)

Max Activating Token Index: 382

Text #1

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.6181. Min Act: -0.0000

Data Index: 1620395 (Python Code)

Max Activating Token Index: 366

Text #2

Max Range: 3.7886. Min Range: -3.7886

Max Act: 2.9549. Min Act: -0.0000

Data Index: 1421431 (Python Code)

Max Activating Token Index: 924

Text #3

Max Range: 3.7886. Min Range: -3.7886

Max Act: 2.8928. Min Act: -0.0000

Data Index: 1422409 (Python Code)

Max Activating Token Index: 429

Text #4

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.0029. Min Act: -0.0000

Data Index: 1504890 (Python Code)

Max Activating Token Index: 718

Text #5

Max Range: 3.7886. Min Range: -3.7886

Max Act: 2.8307. Min Act: -0.0000

Data Index: 1545112 (Python Code)

Max Activating Token Index: 294

Text #6

Max Range: 3.7886. Min Range: -3.7886

Max Act: 2.9089. Min Act: -0.0000

Data Index: 1495322 (Python Code)

Max Activating Token Index: 973

Text #7

Max Range: 3.7886. Min Range: -3.7886

Max Act: 2.8902. Min Act: -0.0000

Data Index: 1607635 (Python Code)

Max Activating Token Index: 295

Text #8

Max Range: 3.7886. Min Range: -3.7886

Max Act: 3.1555. Min Act: -0.0000

Data Index: 1469332 (Python Code)

Max Activating Token Index: 549

Text #9

Max Range: 3.7886. Min Range: -3.7886

Max Act: 2.7951. Min Act: -0.0000

Data Index: 1412581 (Python Code)

Max Activating Token Index: 265

Text #10

Max Range: 3.7886. Min Range: -3.7886

Max Act: 2.7809. Min Act: -0.0000

Data Index: 1442073 (Python Code)

Max Activating Token Index: 988

Text #11

Max Range: 3.7886. Min Range: -3.7886

Max Act: 2.4765. Min Act: -0.0000

Data Index: 1556634 (Python Code)

Max Activating Token Index: 931

Text #12

Max Range: 3.7886. Min Range: -3.7886

Max Act: 2.7217. Min Act: -0.0000

Data Index: 1641602 (Python Code)

Max Activating Token Index: 406

Text #13

Max Range: 3.7886. Min Range: -3.7886

Max Act: 2.7011. Min Act: -0.0000

Data Index: 1529100 (Python Code)

Max Activating Token Index: 121

Text #14

Max Range: 3.7886. Min Range: -3.7886

Max Act: 2.5359. Min Act: -0.0000

Data Index: 1578985 (Python Code)

Max Activating Token Index: 542

Text #15

Max Range: 3.7886. Min Range: -3.7886

Max Act: 2.8029. Min Act: -0.0000

Data Index: 1615133 (Python Code)

Max Activating Token Index: 203

Text #16

Max Range: 3.7886. Min Range: -3.7886

Max Act: 2.6279. Min Act: -0.0000

Data Index: 1436568 (Python Code)

Max Activating Token Index: 684

Text #17

Max Range: 3.7886. Min Range: -3.7886

Max Act: 2.5991. Min Act: -0.0000

Data Index: 1466567 (Python Code)

Max Activating Token Index: 990

Text #18

Max Range: 3.7886. Min Range: -3.7886

Max Act: 2.7159. Min Act: -0.0000

Data Index: 1602128 (Python Code)

Max Activating Token Index: 329

Text #19

Max Range: 3.7886. Min Range: -3.7886

Max Act: 2.5972. Min Act: -0.0000

Data Index: 1565082 (Python Code)

Max Activating Token Index: 225