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

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

Neuron 5772 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3914. Min Range: -4.3914

Max Act: 4.3914. Min Act: -0.0000

Data Index: 1553662 (Python Code)

Max Activating Token Index: 51

Text #1

Max Range: 4.3914. Min Range: -4.3914

Max Act: 4.2671. Min Act: -0.0000

Data Index: 1646367 (Python Code)

Max Activating Token Index: 748

Text #2

Max Range: 4.3914. Min Range: -4.3914

Max Act: 4.1138. Min Act: -0.0000

Data Index: 1434164 (Python Code)

Max Activating Token Index: 147

Text #3

Max Range: 4.3914. Min Range: -4.3914

Max Act: 3.8500. Min Act: -0.0000

Data Index: 515698 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 4.3914. Min Range: -4.3914

Max Act: 3.8349. Min Act: -0.0000

Data Index: 1400397 (Python Code)

Max Activating Token Index: 219

Text #5

Max Range: 4.3914. Min Range: -4.3914

Max Act: 3.8840. Min Act: -0.0000

Data Index: 1396436 (Python Code)

Max Activating Token Index: 316

Text #6

Max Range: 4.3914. Min Range: -4.3914

Max Act: 3.4056. Min Act: -0.0000

Data Index: 1518904 (Python Code)

Max Activating Token Index: 1000

Text #7

Max Range: 4.3914. Min Range: -4.3914

Max Act: 3.6941. Min Act: -0.0000

Data Index: 1602030 (Python Code)

Max Activating Token Index: 954

Text #8

Max Range: 4.3914. Min Range: -4.3914

Max Act: 3.5140. Min Act: -0.0000

Data Index: 1362356 (Python Code)

Max Activating Token Index: 334

Text #9

Max Range: 4.3914. Min Range: -4.3914

Max Act: 3.4643. Min Act: -0.0000

Data Index: 1581716 (Python Code)

Max Activating Token Index: 316

Text #10

Max Range: 4.3914. Min Range: -4.3914

Max Act: 3.4790. Min Act: -0.0000

Data Index: 869399 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 4.3914. Min Range: -4.3914

Max Act: 3.4425. Min Act: -0.0000

Data Index: 1397041 (Python Code)

Max Activating Token Index: 150

Text #12

Max Range: 4.3914. Min Range: -4.3914

Max Act: 3.5326. Min Act: -0.0000

Data Index: 1440670 (Python Code)

Max Activating Token Index: 886

Text #13

Max Range: 4.3914. Min Range: -4.3914

Max Act: 3.3106. Min Act: -0.0000

Data Index: 873114 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 4.3914. Min Range: -4.3914

Max Act: 3.4697. Min Act: -0.0000

Data Index: 316656 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 4.3914. Min Range: -4.3914

Max Act: 3.1354. Min Act: -0.0000

Data Index: 930488 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 4.3914. Min Range: -4.3914

Max Act: 3.3972. Min Act: -0.0000

Data Index: 1630609 (Python Code)

Max Activating Token Index: 268

Text #17

Max Range: 4.3914. Min Range: -4.3914

Max Act: 3.3891. Min Act: -0.0000

Data Index: 1383269 (Python Code)

Max Activating Token Index: 971

Text #18

Max Range: 4.3914. Min Range: -4.3914

Max Act: 3.3366. Min Act: -0.0000

Data Index: 1205363 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 4.3914. Min Range: -4.3914

Max Act: 3.0119. Min Act: -0.0000

Data Index: 1521506 (Python Code)

Max Activating Token Index: 973