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

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

Neuron 564 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: 4.2904. Min Range: -4.2904

Max Act: 4.2904. Min Act: -0.0000

Data Index: 897256 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 4.2904. Min Range: -4.2904

Max Act: 4.0975. Min Act: -0.0000

Data Index: 796055 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 4.2904. Min Range: -4.2904

Max Act: 3.7637. Min Act: -0.0000

Data Index: 984837 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 4.2904. Min Range: -4.2904

Max Act: 3.5370. Min Act: -0.0000

Data Index: 973471 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 4.2904. Min Range: -4.2904

Max Act: 3.5609. Min Act: -0.0000

Data Index: 924140 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 4.2904. Min Range: -4.2904

Max Act: 3.1813. Min Act: -0.0000

Data Index: 636156 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 4.2904. Min Range: -4.2904

Max Act: 3.0269. Min Act: -0.0000

Data Index: 375228 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 4.2904. Min Range: -4.2904

Max Act: 3.1685. Min Act: -0.0000

Data Index: 407876 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 4.2904. Min Range: -4.2904

Max Act: 3.0461. Min Act: -0.0000

Data Index: 563993 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 4.2904. Min Range: -4.2904

Max Act: 3.0340. Min Act: -0.0000

Data Index: 404518 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 4.2904. Min Range: -4.2904

Max Act: 2.8775. Min Act: -0.0000

Data Index: 930859 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 4.2904. Min Range: -4.2904

Max Act: 2.9596. Min Act: -0.0000

Data Index: 90195 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 4.2904. Min Range: -4.2904

Max Act: 2.9452. Min Act: -0.0000

Data Index: 589938 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 4.2904. Min Range: -4.2904

Max Act: 2.9110. Min Act: -0.0000

Data Index: 904266 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 4.2904. Min Range: -4.2904

Max Act: 2.7106. Min Act: -0.0000

Data Index: 1307071 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 4.2904. Min Range: -4.2904

Max Act: 2.8336. Min Act: -0.0000

Data Index: 313671 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 4.2904. Min Range: -4.2904

Max Act: 2.8296. Min Act: -0.0000

Data Index: 974911 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 4.2904. Min Range: -4.2904

Max Act: 2.7912. Min Act: -0.0000

Data Index: 376583 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 4.2904. Min Range: -4.2904

Max Act: 2.7210. Min Act: -0.0000

Data Index: 503339 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 4.2904. Min Range: -4.2904

Max Act: 2.6498. Min Act: -0.0000

Data Index: 1116786 (C4 (Web Text))

Max Activating Token Index: 991