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

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

Neuron 1421 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5757. Min Range: -1.5757

Max Act: 1.5757. Min Act: -0.0000

Data Index: 539114 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 1.5757. Min Range: -1.5757

Max Act: 1.4163. Min Act: -0.0000

Data Index: 409271 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 1.5757. Min Range: -1.5757

Max Act: 1.2836. Min Act: -0.0000

Data Index: 1292026 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 1.5757. Min Range: -1.5757

Max Act: 1.1761. Min Act: -0.0000

Data Index: 286669 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 1.5757. Min Range: -1.5757

Max Act: 1.1369. Min Act: -0.0000

Data Index: 1084306 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.9796. Min Act: -0.0000

Data Index: 426565 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.8662. Min Act: -0.0000

Data Index: 737778 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.9568. Min Act: -0.0000

Data Index: 1300214 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 1.5757. Min Range: -1.5757

Max Act: 1.0322. Min Act: -0.0000

Data Index: 1107125 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.8791. Min Act: -0.0000

Data Index: 1143786 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.8732. Min Act: -0.0000

Data Index: 267211 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.8760. Min Act: -0.0000

Data Index: 60731 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.8775. Min Act: -0.0000

Data Index: 579369 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.8757. Min Act: -0.0000

Data Index: 836948 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.8813. Min Act: -0.0000

Data Index: 108262 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.8051. Min Act: -0.0000

Data Index: 399065 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.8169. Min Act: -0.0000

Data Index: 384797 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1297347 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.7640. Min Act: -0.0000

Data Index: 833768 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 1.5757. Min Range: -1.5757

Max Act: 0.7776. Min Act: -0.0000

Data Index: 1067724 (C4 (Web Text))

Max Activating Token Index: 488