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

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

Neuron 2647 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: 1.7382. Min Range: -1.7382

Max Act: 1.7382. Min Act: -0.0000

Data Index: 640430 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 1.7382. Min Range: -1.7382

Max Act: 1.5724. Min Act: -0.0000

Data Index: 108624 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 1.7382. Min Range: -1.7382

Max Act: 1.2356. Min Act: -0.0000

Data Index: 636855 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 1.7382. Min Range: -1.7382

Max Act: 1.3718. Min Act: -0.0000

Data Index: 381744 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 1.7382. Min Range: -1.7382

Max Act: 1.3071. Min Act: -0.0000

Data Index: 970453 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 1.7382. Min Range: -1.7382

Max Act: 1.1000. Min Act: -0.0000

Data Index: 982455 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 1.7382. Min Range: -1.7382

Max Act: 1.1567. Min Act: -0.0000

Data Index: 1102465 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 1.7382. Min Range: -1.7382

Max Act: 1.1259. Min Act: -0.0000

Data Index: 641908 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 1.7382. Min Range: -1.7382

Max Act: 1.0875. Min Act: -0.0000

Data Index: 1172665 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 1.7382. Min Range: -1.7382

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1130249 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 1.7382. Min Range: -1.7382

Max Act: 1.0146. Min Act: -0.0000

Data Index: 341455 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 1.7382. Min Range: -1.7382

Max Act: 1.0164. Min Act: -0.0000

Data Index: 694000 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 1.7382. Min Range: -1.7382

Max Act: 1.0192. Min Act: -0.0000

Data Index: 1265968 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 1.7382. Min Range: -1.7382

Max Act: 1.0011. Min Act: -0.0000

Data Index: 859549 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 1.7382. Min Range: -1.7382

Max Act: 0.9071. Min Act: -0.0000

Data Index: 651370 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 1.7382. Min Range: -1.7382

Max Act: 0.9472. Min Act: -0.0000

Data Index: 581154 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 1.7382. Min Range: -1.7382

Max Act: 0.9018. Min Act: -0.0000

Data Index: 25015 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.7382. Min Range: -1.7382

Max Act: 0.8771. Min Act: -0.0000

Data Index: 965143 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 1.7382. Min Range: -1.7382

Max Act: 0.9468. Min Act: -0.0000

Data Index: 200363 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 1.7382. Min Range: -1.7382

Max Act: 0.8833. Min Act: -0.0000

Data Index: 689281 (C4 (Web Text))

Max Activating Token Index: 350