Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1363 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.4058. Min Act: -0.0000

Data Index: 812466 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.4281. Min Act: -0.0000

Data Index: 1213038 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3732. Min Act: -0.0000

Data Index: 140622 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3963. Min Act: -0.0000

Data Index: 844118 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3890. Min Act: -0.0001

Data Index: 474351 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3815. Min Act: -0.0000

Data Index: 1066368 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3350. Min Act: -0.0001

Data Index: 962321 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3572. Min Act: -0.0000

Data Index: 1290177 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3580. Min Act: -0.0000

Data Index: 1193298 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3529. Min Act: -0.0000

Data Index: 731892 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3605. Min Act: -0.0001

Data Index: 396935 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3580. Min Act: -0.0000

Data Index: 115032 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3550. Min Act: -0.0001

Data Index: 985789 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3364. Min Act: -0.0001

Data Index: 371684 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3420. Min Act: -0.0000

Data Index: 956011 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3276. Min Act: -0.0001

Data Index: 18785 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3598. Min Act: -0.0001

Data Index: 146679 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3285. Min Act: -0.0000

Data Index: 1009718 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3291. Min Act: -0.0000

Data Index: 930708 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3327. Min Act: -0.0000

Data Index: 292880 (C4 (Web Text))

Max Activating Token Index: 39