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

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

Neuron 1980 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: 2.9183. Min Range: -2.9183

Max Act: 2.8281. Min Act: -0.0001

Data Index: 1129385 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.7372. Min Act: -0.0000

Data Index: 525751 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.7388. Min Act: -0.0000

Data Index: 284594 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.5368. Min Act: -0.0000

Data Index: 69436 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.5659. Min Act: -0.0000

Data Index: 77660 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.5752. Min Act: -0.0000

Data Index: 603277 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.9183. Min Act: -0.0001

Data Index: 346291 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.7694. Min Act: -0.0001

Data Index: 1224328 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.1811. Min Act: -0.0000

Data Index: 297712 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.3882. Min Act: -0.0000

Data Index: 87792 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.4911. Min Act: -0.0000

Data Index: 706860 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.5530. Min Act: -0.0000

Data Index: 544283 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.5567. Min Act: -0.0000

Data Index: 433968 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.1944. Min Act: -0.0000

Data Index: 893928 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.4267. Min Act: -0.0000

Data Index: 1340103 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.4084. Min Act: -0.0000

Data Index: 986016 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.2652. Min Act: -0.0000

Data Index: 1073988 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.1282. Min Act: -0.0000

Data Index: 711529 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.3386. Min Act: -0.0001

Data Index: 1185822 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.3373. Min Act: -0.0000

Data Index: 651326 (C4 (Web Text))

Max Activating Token Index: 116