Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3683 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1140954 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.2292. Min Act: -0.0000

Data Index: 762142 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.2283. Min Act: -0.0000

Data Index: 296329 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.2205. Min Act: -0.0001

Data Index: 887746 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.2188. Min Act: -0.0001

Data Index: 432017 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.2053. Min Act: -0.0000

Data Index: 386159 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.1938. Min Act: -0.0001

Data Index: 289169 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.1971. Min Act: -0.0001

Data Index: 1302363 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.2065. Min Act: -0.0000

Data Index: 495818 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.1964. Min Act: -0.0000

Data Index: 396657 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.1889. Min Act: -0.0001

Data Index: 922965 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.1802. Min Act: -0.0000

Data Index: 528719 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.1949. Min Act: -0.0000

Data Index: 850685 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.1868. Min Act: -0.0001

Data Index: 70340 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.1920. Min Act: -0.0001

Data Index: 340222 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.1824. Min Act: -0.0001

Data Index: 1102908 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.1733. Min Act: -0.0000

Data Index: 158760 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.1730. Min Act: -0.0000

Data Index: 595501 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.1779. Min Act: -0.0000

Data Index: 753108 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.3196. Min Range: -0.3196

Max Act: 0.1688. Min Act: -0.0000

Data Index: 343535 (C4 (Web Text))

Max Activating Token Index: 63