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

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

Neuron 467 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: 4.2396. Min Range: -4.2396

Max Act: 4.2396. Min Act: -0.0000

Data Index: 49864 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 4.2396. Min Range: -4.2396

Max Act: 3.8762. Min Act: -0.0000

Data Index: 278118 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 4.2396. Min Range: -4.2396

Max Act: 3.5156. Min Act: -0.0000

Data Index: 997526 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 4.2396. Min Range: -4.2396

Max Act: 3.8254. Min Act: -0.0000

Data Index: 667991 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 4.2396. Min Range: -4.2396

Max Act: 3.4518. Min Act: -0.0000

Data Index: 275865 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 4.2396. Min Range: -4.2396

Max Act: 2.9066. Min Act: -0.0000

Data Index: 26537 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 4.2396. Min Range: -4.2396

Max Act: 3.1975. Min Act: -0.0000

Data Index: 1233377 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 4.2396. Min Range: -4.2396

Max Act: 3.3330. Min Act: -0.0000

Data Index: 54251 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 4.2396. Min Range: -4.2396

Max Act: 3.0216. Min Act: -0.0000

Data Index: 879555 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 4.2396. Min Range: -4.2396

Max Act: 3.1506. Min Act: -0.0000

Data Index: 1233077 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 4.2396. Min Range: -4.2396

Max Act: 3.2797. Min Act: -0.0000

Data Index: 266932 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 4.2396. Min Range: -4.2396

Max Act: 3.0944. Min Act: -0.0000

Data Index: 237221 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 4.2396. Min Range: -4.2396

Max Act: 3.1043. Min Act: -0.0000

Data Index: 443947 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 4.2396. Min Range: -4.2396

Max Act: 3.0815. Min Act: -0.0000

Data Index: 1598342 (Python Code)

Max Activating Token Index: 435

Text #14

Max Range: 4.2396. Min Range: -4.2396

Max Act: 3.2058. Min Act: -0.0000

Data Index: 479804 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 4.2396. Min Range: -4.2396

Max Act: 3.1955. Min Act: -0.0000

Data Index: 911789 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 4.2396. Min Range: -4.2396

Max Act: 3.0528. Min Act: -0.0000

Data Index: 384279 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 4.2396. Min Range: -4.2396

Max Act: 2.9098. Min Act: -0.0000

Data Index: 1490936 (Python Code)

Max Activating Token Index: 838

Text #18

Max Range: 4.2396. Min Range: -4.2396

Max Act: 2.8617. Min Act: -0.0000

Data Index: 968895 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 4.2396. Min Range: -4.2396

Max Act: 3.0008. Min Act: -0.0000

Data Index: 190659 (C4 (Web Text))

Max Activating Token Index: 177