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

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

Neuron 619 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.5935. Min Act: -0.0000

Data Index: 1003898 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.1813. Min Act: -0.0000

Data Index: 837370 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.1363. Min Act: -0.0000

Data Index: 574170 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.2280. Min Act: -0.0000

Data Index: 838764 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.0652. Min Act: -0.0000

Data Index: 514985 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.0201. Min Act: -0.0000

Data Index: 474448 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.0014. Min Act: -0.0000

Data Index: 1147975 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.1015. Min Act: -0.0000

Data Index: 341248 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.0513. Min Act: -0.0000

Data Index: 416004 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.0148. Min Act: -0.0000

Data Index: 1273920 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 3.5935. Min Range: -3.5935

Max Act: 2.9715. Min Act: -0.0000

Data Index: 204280 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 3.5935. Min Range: -3.5935

Max Act: 2.9451. Min Act: -0.0000

Data Index: 716407 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 3.5935. Min Range: -3.5935

Max Act: 2.8027. Min Act: -0.0000

Data Index: 898633 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 3.5935. Min Range: -3.5935

Max Act: 2.9117. Min Act: -0.0000

Data Index: 873990 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 3.5935. Min Range: -3.5935

Max Act: 2.8856. Min Act: -0.0000

Data Index: 791810 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 3.5935. Min Range: -3.5935

Max Act: 2.8777. Min Act: -0.0000

Data Index: 570258 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 3.5935. Min Range: -3.5935

Max Act: 2.8533. Min Act: -0.0000

Data Index: 659285 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 3.5935. Min Range: -3.5935

Max Act: 2.9956. Min Act: -0.0000

Data Index: 1191971 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 3.5935. Min Range: -3.5935

Max Act: 2.9861. Min Act: -0.0000

Data Index: 415903 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 3.5935. Min Range: -3.5935

Max Act: 2.8244. Min Act: -0.0000

Data Index: 1296977 (C4 (Web Text))

Max Activating Token Index: 827