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

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

Neuron 3487 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9920. Min Act: -0.0001

Data Index: 198631 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.0249. Min Range: -1.0249

Max Act: 1.0225. Min Act: -0.0001

Data Index: 572670 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 1.0249. Min Range: -1.0249

Max Act: 1.0249. Min Act: -0.0001

Data Index: 154991 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9576. Min Act: -0.0001

Data Index: 305351 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9345. Min Act: -0.0001

Data Index: 757628 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9176. Min Act: -0.0001

Data Index: 1275939 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9435. Min Act: -0.0001

Data Index: 180210 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9960. Min Act: -0.0001

Data Index: 1464504 (Python Code)

Max Activating Token Index: 438

Text #8

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8998. Min Act: -0.0001

Data Index: 444958 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8277. Min Act: -0.0001

Data Index: 253137 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9184. Min Act: -0.0001

Data Index: 475877 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8830. Min Act: -0.0001

Data Index: 1372730 (Python Code)

Max Activating Token Index: 113

Text #12

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8313. Min Act: -0.0001

Data Index: 949824 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9022. Min Act: -0.0001

Data Index: 145869 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8803. Min Act: -0.0001

Data Index: 1246490 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9325. Min Act: -0.0001

Data Index: 1412286 (Python Code)

Max Activating Token Index: 76

Text #16

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8934. Min Act: -0.0001

Data Index: 1084957 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8930. Min Act: -0.0001

Data Index: 347986 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8736. Min Act: -0.0001

Data Index: 80825 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9082. Min Act: -0.0001

Data Index: 1225201 (C4 (Web Text))

Max Activating Token Index: 322