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

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

Neuron 2051 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1845. Min Range: -4.1845

Max Act: 4.1845. Min Act: -0.0001

Data Index: 1240566 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.8374. Min Act: -0.0000

Data Index: 765073 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.9820. Min Act: -0.0001

Data Index: 622833 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.7814. Min Act: -0.0000

Data Index: 918872 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.6963. Min Act: -0.0000

Data Index: 52751 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.4991. Min Act: -0.0000

Data Index: 1106976 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.4174. Min Act: -0.0001

Data Index: 562461 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 4.1845. Min Range: -4.1845

Max Act: 2.9775. Min Act: -0.0001

Data Index: 536332 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.3738. Min Act: -0.0000

Data Index: 1238321 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.4400. Min Act: -0.0000

Data Index: 38474 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.2543. Min Act: -0.0001

Data Index: 433246 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.2229. Min Act: -0.0000

Data Index: 724044 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.3510. Min Act: -0.0001

Data Index: 980321 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.1807. Min Act: -0.0001

Data Index: 920070 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.0098. Min Act: -0.0000

Data Index: 1141469 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 4.1845. Min Range: -4.1845

Max Act: 2.8514. Min Act: -0.0000

Data Index: 856970 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.2586. Min Act: -0.0001

Data Index: 1244588 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.2040. Min Act: -0.0000

Data Index: 1340088 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.2336. Min Act: -0.0001

Data Index: 430361 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 4.1845. Min Range: -4.1845

Max Act: 3.0397. Min Act: -0.0001

Data Index: 78036 (C4 (Web Text))

Max Activating Token Index: 311