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

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

Neuron 2149 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.7172. Min Act: -0.0001

Data Index: 545951 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.7127. Min Act: -0.0001

Data Index: 763481 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6822. Min Act: -0.0001

Data Index: 1305672 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6589. Min Act: -0.0001

Data Index: 183694 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6663. Min Act: -0.0001

Data Index: 293619 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6755. Min Act: -0.0001

Data Index: 1291045 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6174. Min Act: -0.0001

Data Index: 780780 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6573. Min Act: -0.0001

Data Index: 1043806 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6437. Min Act: -0.0001

Data Index: 1455125 (Python Code)

Max Activating Token Index: 515

Text #9

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6795. Min Act: -0.0001

Data Index: 389346 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6433. Min Act: -0.0001

Data Index: 1627509 (Python Code)

Max Activating Token Index: 286

Text #11

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6612. Min Act: -0.0001

Data Index: 1187924 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5706. Min Act: -0.0001

Data Index: 1338236 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5811. Min Act: -0.0001

Data Index: 588996 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5921. Min Act: -0.0001

Data Index: 636973 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6036. Min Act: -0.0001

Data Index: 184866 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5826. Min Act: -0.0001

Data Index: 911803 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5591. Min Act: -0.0001

Data Index: 112368 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5955. Min Act: -0.0001

Data Index: 1354932 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5962. Min Act: -0.0001

Data Index: 1219100 (C4 (Web Text))

Max Activating Token Index: 711