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

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

Neuron 5346 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2844. Min Range: -1.2844

Max Act: 1.2844. Min Act: -0.0000

Data Index: 992661 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 1.2844. Min Range: -1.2844

Max Act: 1.1737. Min Act: -0.0000

Data Index: 1196957 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 1.2844. Min Range: -1.2844

Max Act: 1.1101. Min Act: -0.0000

Data Index: 150631 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 1.2844. Min Range: -1.2844

Max Act: 1.1620. Min Act: -0.0000

Data Index: 408090 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 1.2844. Min Range: -1.2844

Max Act: 1.1495. Min Act: -0.0000

Data Index: 1301807 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 1.2844. Min Range: -1.2844

Max Act: 1.1580. Min Act: -0.0000

Data Index: 261640 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 1.2844. Min Range: -1.2844

Max Act: 1.1010. Min Act: -0.0000

Data Index: 549953 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 1.2844. Min Range: -1.2844

Max Act: 1.0514. Min Act: -0.0000

Data Index: 245608 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 1.2844. Min Range: -1.2844

Max Act: 1.0443. Min Act: -0.0000

Data Index: 411093 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 1.2844. Min Range: -1.2844

Max Act: 1.0683. Min Act: -0.0000

Data Index: 856576 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 1.2844. Min Range: -1.2844

Max Act: 1.0120. Min Act: -0.0000

Data Index: 99206 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 1.2844. Min Range: -1.2844

Max Act: 1.0208. Min Act: -0.0000

Data Index: 631980 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 1.2844. Min Range: -1.2844

Max Act: 1.0424. Min Act: -0.0000

Data Index: 178057 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 1.2844. Min Range: -1.2844

Max Act: 1.1010. Min Act: -0.0000

Data Index: 206401 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 1.2844. Min Range: -1.2844

Max Act: 1.0649. Min Act: -0.0000

Data Index: 240516 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 1.2844. Min Range: -1.2844

Max Act: 1.0956. Min Act: -0.0000

Data Index: 841330 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 1.2844. Min Range: -1.2844

Max Act: 1.0160. Min Act: -0.0000

Data Index: 37269 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 1.2844. Min Range: -1.2844

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1310764 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 1.2844. Min Range: -1.2844

Max Act: 1.0111. Min Act: -0.0000

Data Index: 793168 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 1.2844. Min Range: -1.2844

Max Act: 0.9972. Min Act: -0.0000

Data Index: 633381 (C4 (Web Text))

Max Activating Token Index: 904