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

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

Neuron 54 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3383. Min Range: -2.3383

Max Act: 2.3073. Min Act: -0.0000

Data Index: 829081 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 2.3383. Min Range: -2.3383

Max Act: 2.3383. Min Act: -0.0000

Data Index: 332118 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 2.3383. Min Range: -2.3383

Max Act: 2.1907. Min Act: -0.0000

Data Index: 1317585 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 2.3383. Min Range: -2.3383

Max Act: 2.0711. Min Act: -0.0000

Data Index: 1548281 (Python Code)

Max Activating Token Index: 180

Text #4

Max Range: 2.3383. Min Range: -2.3383

Max Act: 1.9258. Min Act: -0.0000

Data Index: 367270 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 2.3383. Min Range: -2.3383

Max Act: 1.7795. Min Act: -0.0000

Data Index: 517799 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 2.3383. Min Range: -2.3383

Max Act: 1.7847. Min Act: -0.0000

Data Index: 312137 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 2.3383. Min Range: -2.3383

Max Act: 1.6050. Min Act: -0.0000

Data Index: 1394296 (Python Code)

Max Activating Token Index: 266

Text #8

Max Range: 2.3383. Min Range: -2.3383

Max Act: 1.8761. Min Act: -0.0000

Data Index: 87371 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 2.3383. Min Range: -2.3383

Max Act: 1.5546. Min Act: -0.0000

Data Index: 4251 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 2.3383. Min Range: -2.3383

Max Act: 1.6826. Min Act: -0.0000

Data Index: 651646 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 2.3383. Min Range: -2.3383

Max Act: 1.6104. Min Act: -0.0000

Data Index: 1393079 (Python Code)

Max Activating Token Index: 775

Text #12

Max Range: 2.3383. Min Range: -2.3383

Max Act: 1.5699. Min Act: -0.0000

Data Index: 384713 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 2.3383. Min Range: -2.3383

Max Act: 1.4319. Min Act: -0.0000

Data Index: 155408 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 2.3383. Min Range: -2.3383

Max Act: 1.4963. Min Act: -0.0000

Data Index: 988810 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 2.3383. Min Range: -2.3383

Max Act: 1.4134. Min Act: -0.0000

Data Index: 1206061 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 2.3383. Min Range: -2.3383

Max Act: 1.4977. Min Act: -0.0000

Data Index: 384514 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 2.3383. Min Range: -2.3383

Max Act: 1.3982. Min Act: -0.0000

Data Index: 811235 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 2.3383. Min Range: -2.3383

Max Act: 1.5369. Min Act: -0.0000

Data Index: 583415 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 2.3383. Min Range: -2.3383

Max Act: 1.3596. Min Act: -0.0000

Data Index: 88499 (C4 (Web Text))

Max Activating Token Index: 767