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

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

Neuron 5487 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.8196. Min Act: -0.0000

Data Index: 1600625 (Python Code)

Max Activating Token Index: 616

Text #1

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.7760. Min Act: -0.0000

Data Index: 1414504 (Python Code)

Max Activating Token Index: 309

Text #2

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.7439. Min Act: -0.0000

Data Index: 1380227 (Python Code)

Max Activating Token Index: 640

Text #3

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.6479. Min Act: -0.0000

Data Index: 1521642 (Python Code)

Max Activating Token Index: 281

Text #4

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.5848. Min Act: -0.0000

Data Index: 1637948 (Python Code)

Max Activating Token Index: 637

Text #5

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.4709. Min Act: -0.0000

Data Index: 839400 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1007965 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.4461. Min Act: -0.0000

Data Index: 505908 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.4270. Min Act: -0.0000

Data Index: 70927 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.3247. Min Act: -0.0000

Data Index: 718640 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.3979. Min Act: -0.0000

Data Index: 1424482 (Python Code)

Max Activating Token Index: 682

Text #11

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.3068. Min Act: -0.0000

Data Index: 1545403 (Python Code)

Max Activating Token Index: 151

Text #12

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.3532. Min Act: -0.0000

Data Index: 1606811 (Python Code)

Max Activating Token Index: 189

Text #13

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.2942. Min Act: -0.0000

Data Index: 1432497 (Python Code)

Max Activating Token Index: 952

Text #14

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.2879. Min Act: -0.0000

Data Index: 1458772 (Python Code)

Max Activating Token Index: 516

Text #15

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.2762. Min Act: -0.0000

Data Index: 1609690 (Python Code)

Max Activating Token Index: 361

Text #16

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.2733. Min Act: -0.0000

Data Index: 331070 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.3462. Min Act: -0.0000

Data Index: 844741 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.2211. Min Act: -0.0000

Data Index: 1611599 (Python Code)

Max Activating Token Index: 483

Text #19

Max Range: 1.8196. Min Range: -1.8196

Max Act: 1.2179. Min Act: -0.0000

Data Index: 792058 (C4 (Web Text))

Max Activating Token Index: 693