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

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

Neuron 4967 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: 1.1987. Min Range: -1.1987

Max Act: 1.1770. Min Act: -0.0001

Data Index: 184661 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 1.1987. Min Range: -1.1987

Max Act: 1.1987. Min Act: -0.0001

Data Index: 137463 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 1.1987. Min Range: -1.1987

Max Act: 1.0401. Min Act: -0.0001

Data Index: 1030945 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.9977. Min Act: -0.0001

Data Index: 233408 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 1.1987. Min Range: -1.1987

Max Act: 1.0402. Min Act: -0.0001

Data Index: 13100 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.9122. Min Act: -0.0001

Data Index: 108348 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 1.1987. Min Range: -1.1987

Max Act: 1.0161. Min Act: -0.0001

Data Index: 434208 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8880. Min Act: -0.0001

Data Index: 262956 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 1.1987. Min Range: -1.1987

Max Act: 1.0414. Min Act: -0.0001

Data Index: 766593 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.9255. Min Act: -0.0001

Data Index: 198281 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.7536. Min Act: -0.0001

Data Index: 910539 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8103. Min Act: -0.0001

Data Index: 877330 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.9700. Min Act: -0.0001

Data Index: 571064 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.9651. Min Act: -0.0001

Data Index: 1022680 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8786. Min Act: -0.0001

Data Index: 278531 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8998. Min Act: -0.0001

Data Index: 394903 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8411. Min Act: -0.0001

Data Index: 894254 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8534. Min Act: -0.0001

Data Index: 868909 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8498. Min Act: -0.0001

Data Index: 763839 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8229. Min Act: -0.0001

Data Index: 334915 (C4 (Web Text))

Max Activating Token Index: 255