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

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

Neuron 2038 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.8094. Min Act: -0.0001

Data Index: 1083139 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.8023. Min Act: -0.0002

Data Index: 661400 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7835. Min Act: -0.0002

Data Index: 984055 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7782. Min Act: -0.0002

Data Index: 127449 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7973. Min Act: -0.0002

Data Index: 1224221 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7610. Min Act: -0.0001

Data Index: 808617 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7632. Min Act: -0.0001

Data Index: 1018548 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7116. Min Act: -0.0002

Data Index: 88463 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.6415. Min Act: -0.0002

Data Index: 824332 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.6988. Min Act: -0.0001

Data Index: 1191062 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7157. Min Act: -0.0002

Data Index: 1293183 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7422. Min Act: -0.0001

Data Index: 1263415 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7167. Min Act: -0.0001

Data Index: 161750 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7785. Min Act: -0.0002

Data Index: 345522 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7215. Min Act: -0.0002

Data Index: 880237 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.6738. Min Act: -0.0001

Data Index: 420480 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7175. Min Act: -0.0002

Data Index: 459329 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.6662. Min Act: -0.0002

Data Index: 716596 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7101. Min Act: -0.0001

Data Index: 188181 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.8094. Min Range: -0.8094

Max Act: 0.7257. Min Act: -0.0002

Data Index: 1010687 (C4 (Web Text))

Max Activating Token Index: 1003