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

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

Neuron 4408 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.3236. Min Act: -0.0001

Data Index: 293962 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.3212. Min Act: -0.0001

Data Index: 1204701 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1147052 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1497312 (Python Code)

Max Activating Token Index: 99

Text #4

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2779. Min Act: -0.0001

Data Index: 100696 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2623. Min Act: -0.0001

Data Index: 192092 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2583. Min Act: -0.0000

Data Index: 593974 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2582. Min Act: -0.0001

Data Index: 972828 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2685. Min Act: -0.0000

Data Index: 512341 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2521. Min Act: -0.0000

Data Index: 934258 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2439. Min Act: -0.0000

Data Index: 450538 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2387. Min Act: -0.0000

Data Index: 562688 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2353. Min Act: -0.0000

Data Index: 430959 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2525. Min Act: -0.0000

Data Index: 516604 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2506. Min Act: -0.0001

Data Index: 270213 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2451. Min Act: -0.0000

Data Index: 389092 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1300010 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2236. Min Act: -0.0001

Data Index: 993627 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2083. Min Act: -0.0000

Data Index: 424597 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.3236. Min Range: -0.3236

Max Act: 0.2274. Min Act: -0.0001

Data Index: 1150547 (C4 (Web Text))

Max Activating Token Index: 438