Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3230 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.3257. Min Act: -0.0001

Data Index: 967018 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.2680. Min Act: -0.0001

Data Index: 999428 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.5010. Min Act: -0.0001

Data Index: 558640 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 3.5010. Min Range: -3.5010

Max Act: 3.2352. Min Act: -0.0001

Data Index: 721754 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.9331. Min Act: -0.0001

Data Index: 254230 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.4429. Min Act: -0.0001

Data Index: 672206 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.2663. Min Act: -0.0001

Data Index: 83366 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.2730. Min Act: -0.0001

Data Index: 1160687 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.1204. Min Act: -0.0001

Data Index: 717213 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 3.5010. Min Range: -3.5010

Max Act: 1.9385. Min Act: -0.0001

Data Index: 288898 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 3.5010. Min Range: -3.5010

Max Act: 1.9070. Min Act: -0.0001

Data Index: 35415 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.0254. Min Act: -0.0001

Data Index: 862542 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.0916. Min Act: -0.0001

Data Index: 155148 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 3.5010. Min Range: -3.5010

Max Act: 1.8935. Min Act: -0.0001

Data Index: 437789 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 3.5010. Min Range: -3.5010

Max Act: 1.8222. Min Act: -0.0001

Data Index: 437809 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 3.5010. Min Range: -3.5010

Max Act: 2.0370. Min Act: -0.0001

Data Index: 266945 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 3.5010. Min Range: -3.5010

Max Act: 1.9079. Min Act: -0.0001

Data Index: 246012 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 3.5010. Min Range: -3.5010

Max Act: 1.9108. Min Act: -0.0001

Data Index: 241955 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 3.5010. Min Range: -3.5010

Max Act: 1.8577. Min Act: -0.0001

Data Index: 281502 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 3.5010. Min Range: -3.5010

Max Act: 1.9319. Min Act: -0.0001

Data Index: 1249137 (C4 (Web Text))

Max Activating Token Index: 893