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

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

Neuron 2391 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: 2.1312. Min Range: -2.1312

Max Act: 2.1312. Min Act: -0.0000

Data Index: 1510081 (Python Code)

Max Activating Token Index: 667

Text #1

Max Range: 2.1312. Min Range: -2.1312

Max Act: 2.0715. Min Act: -0.0001

Data Index: 1575576 (Python Code)

Max Activating Token Index: 388

Text #2

Max Range: 2.1312. Min Range: -2.1312

Max Act: 2.0323. Min Act: -0.0001

Data Index: 1447478 (Python Code)

Max Activating Token Index: 484

Text #3

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.9122. Min Act: -0.0000

Data Index: 1510002 (Python Code)

Max Activating Token Index: 691

Text #4

Max Range: 2.1312. Min Range: -2.1312

Max Act: 2.0832. Min Act: -0.0000

Data Index: 1399770 (Python Code)

Max Activating Token Index: 908

Text #5

Max Range: 2.1312. Min Range: -2.1312

Max Act: 2.0586. Min Act: -0.0001

Data Index: 1530647 (Python Code)

Max Activating Token Index: 313

Text #6

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.9070. Min Act: -0.0000

Data Index: 1589795 (Python Code)

Max Activating Token Index: 191

Text #7

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.5937. Min Act: -0.0001

Data Index: 1642514 (Python Code)

Max Activating Token Index: 749

Text #8

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.6322. Min Act: -0.0000

Data Index: 1250912 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.6979. Min Act: -0.0000

Data Index: 1458858 (Python Code)

Max Activating Token Index: 812

Text #10

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.6987. Min Act: -0.0000

Data Index: 1500695 (Python Code)

Max Activating Token Index: 483

Text #11

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.6989. Min Act: -0.0001

Data Index: 1437970 (Python Code)

Max Activating Token Index: 107

Text #12

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.6140. Min Act: -0.0000

Data Index: 1368687 (Python Code)

Max Activating Token Index: 563

Text #13

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.6654. Min Act: -0.0001

Data Index: 712850 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.7141. Min Act: -0.0000

Data Index: 1530485 (Python Code)

Max Activating Token Index: 148

Text #15

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.5415. Min Act: -0.0001

Data Index: 263574 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.4652. Min Act: -0.0001

Data Index: 1461150 (Python Code)

Max Activating Token Index: 39

Text #17

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.5746. Min Act: -0.0001

Data Index: 317009 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.4094. Min Act: -0.0001

Data Index: 239643 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 2.1312. Min Range: -2.1312

Max Act: 1.4728. Min Act: -0.0000

Data Index: 115990 (C4 (Web Text))

Max Activating Token Index: 645