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

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

Neuron 1516 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1639851 (Python Code)

Max Activating Token Index: 141

Text #1

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.7509. Min Act: -0.0000

Data Index: 1605152 (Python Code)

Max Activating Token Index: 260

Text #2

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.5650. Min Act: -0.0000

Data Index: 1507599 (Python Code)

Max Activating Token Index: 114

Text #3

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1451529 (Python Code)

Max Activating Token Index: 773

Text #4

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1562622 (Python Code)

Max Activating Token Index: 849

Text #5

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.4711. Min Act: -0.0000

Data Index: 1464759 (Python Code)

Max Activating Token Index: 1013

Text #6

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1558602 (Python Code)

Max Activating Token Index: 738

Text #7

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1382606 (Python Code)

Max Activating Token Index: 389

Text #8

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1644031 (Python Code)

Max Activating Token Index: 13

Text #9

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.3833. Min Act: -0.0000

Data Index: 1409615 (Python Code)

Max Activating Token Index: 687

Text #10

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.3710. Min Act: -0.0000

Data Index: 1490314 (Python Code)

Max Activating Token Index: 108

Text #11

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.3709. Min Act: -0.0000

Data Index: 1409936 (Python Code)

Max Activating Token Index: 963

Text #12

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1511236 (Python Code)

Max Activating Token Index: 409

Text #13

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.3501. Min Act: -0.0000

Data Index: 1603015 (Python Code)

Max Activating Token Index: 1015

Text #14

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.3079. Min Act: -0.0000

Data Index: 1390006 (Python Code)

Max Activating Token Index: 984

Text #15

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.3070. Min Act: -0.0000

Data Index: 1466159 (Python Code)

Max Activating Token Index: 409

Text #16

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1618271 (Python Code)

Max Activating Token Index: 1017

Text #17

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.3579. Min Act: -0.0000

Data Index: 1589521 (Python Code)

Max Activating Token Index: 459

Text #18

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1531812 (Python Code)

Max Activating Token Index: 869

Text #19

Max Range: 0.7642. Min Range: -0.7642

Max Act: 0.3451. Min Act: -0.0000

Data Index: 1491017 (Python Code)

Max Activating Token Index: 307