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

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

Neuron 3349 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1975. Min Range: -1.1975

Max Act: 1.1975. Min Act: -0.0001

Data Index: 104501 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 1.1975. Min Range: -1.1975

Max Act: 1.1511. Min Act: -0.0001

Data Index: 1186058 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 1.1975. Min Range: -1.1975

Max Act: 0.9236. Min Act: -0.0001

Data Index: 1178414 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 1.1975. Min Range: -1.1975

Max Act: 0.9918. Min Act: -0.0001

Data Index: 328042 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 1.1975. Min Range: -1.1975

Max Act: 1.0382. Min Act: -0.0001

Data Index: 87150 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 1.1975. Min Range: -1.1975

Max Act: 1.0114. Min Act: -0.0001

Data Index: 1190930 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 1.1975. Min Range: -1.1975

Max Act: 0.9052. Min Act: -0.0001

Data Index: 673447 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 1.1975. Min Range: -1.1975

Max Act: 0.9693. Min Act: -0.0001

Data Index: 427391 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 1.1975. Min Range: -1.1975

Max Act: 0.9194. Min Act: -0.0001

Data Index: 772611 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 1.1975. Min Range: -1.1975

Max Act: 0.9770. Min Act: -0.0001

Data Index: 1309861 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 1.1975. Min Range: -1.1975

Max Act: 0.9001. Min Act: -0.0001

Data Index: 668011 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 1.1975. Min Range: -1.1975

Max Act: 0.9171. Min Act: -0.0001

Data Index: 355124 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 1.1975. Min Range: -1.1975

Max Act: 0.8978. Min Act: -0.0001

Data Index: 1261128 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 1.1975. Min Range: -1.1975

Max Act: 0.8648. Min Act: -0.0001

Data Index: 112642 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 1.1975. Min Range: -1.1975

Max Act: 0.9282. Min Act: -0.0001

Data Index: 1118866 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 1.1975. Min Range: -1.1975

Max Act: 0.9780. Min Act: -0.0001

Data Index: 309327 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 1.1975. Min Range: -1.1975

Max Act: 0.8546. Min Act: -0.0001

Data Index: 376534 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 1.1975. Min Range: -1.1975

Max Act: 0.8195. Min Act: -0.0001

Data Index: 577742 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 1.1975. Min Range: -1.1975

Max Act: 0.8076. Min Act: -0.0001

Data Index: 1296835 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 1.1975. Min Range: -1.1975

Max Act: 0.7910. Min Act: -0.0001

Data Index: 489396 (C4 (Web Text))

Max Activating Token Index: 994