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

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

Neuron 3390 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.6844. Min Act: -0.0000

Data Index: 986500 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.5108. Min Act: -0.0000

Data Index: 1177471 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.4085. Min Act: -0.0000

Data Index: 343103 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.4068. Min Act: -0.0000

Data Index: 141972 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.4838. Min Act: -0.0000

Data Index: 1179325 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.3548. Min Act: -0.0000

Data Index: 561787 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.3731. Min Act: -0.0000

Data Index: 947590 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.2474. Min Act: -0.0000

Data Index: 143673 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.2420. Min Act: -0.0000

Data Index: 131407 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.2178. Min Act: -0.0000

Data Index: 171750 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.2172. Min Act: -0.0000

Data Index: 1158340 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.1523. Min Act: 0.0000

Data Index: 1032014 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.1976. Min Act: -0.0000

Data Index: 893175 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.1136. Min Act: -0.0000

Data Index: 125800 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.0906. Min Act: -0.0000

Data Index: 250823 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 1.6844. Min Range: -1.6844

Max Act: 0.9903. Min Act: -0.0000

Data Index: 1261637 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.0378. Min Act: -0.0000

Data Index: 567796 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.0384. Min Act: -0.0000

Data Index: 1258593 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 1.6844. Min Range: -1.6844

Max Act: 0.9768. Min Act: -0.0000

Data Index: 636668 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 1.6844. Min Range: -1.6844

Max Act: 1.0335. Min Act: -0.0000

Data Index: 138853 (C4 (Web Text))

Max Activating Token Index: 990