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

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

Neuron 4124 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: 4.9980. Min Range: -4.9980

Max Act: 4.9980. Min Act: -0.0001

Data Index: 668278 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 4.9980. Min Range: -4.9980

Max Act: 4.0954. Min Act: -0.0000

Data Index: 875934 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 4.9980. Min Range: -4.9980

Max Act: 3.4790. Min Act: -0.0001

Data Index: 415423 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 4.9980. Min Range: -4.9980

Max Act: 3.6493. Min Act: -0.0001

Data Index: 873591 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 4.9980. Min Range: -4.9980

Max Act: 2.8009. Min Act: -0.0001

Data Index: 1334632 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 4.9980. Min Range: -4.9980

Max Act: 3.1738. Min Act: -0.0001

Data Index: 222695 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 4.9980. Min Range: -4.9980

Max Act: 3.4629. Min Act: -0.0001

Data Index: 1056165 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 4.9980. Min Range: -4.9980

Max Act: 3.2419. Min Act: -0.0001

Data Index: 81891 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 4.9980. Min Range: -4.9980

Max Act: 3.0663. Min Act: -0.0001

Data Index: 1123346 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 4.9980. Min Range: -4.9980

Max Act: 3.3573. Min Act: -0.0001

Data Index: 215108 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 4.9980. Min Range: -4.9980

Max Act: 3.0427. Min Act: -0.0001

Data Index: 484672 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 4.9980. Min Range: -4.9980

Max Act: 3.1574. Min Act: -0.0001

Data Index: 207576 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 4.9980. Min Range: -4.9980

Max Act: 2.9401. Min Act: -0.0001

Data Index: 317447 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 4.9980. Min Range: -4.9980

Max Act: 2.7790. Min Act: -0.0000

Data Index: 969382 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 4.9980. Min Range: -4.9980

Max Act: 3.2134. Min Act: -0.0001

Data Index: 649196 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 4.9980. Min Range: -4.9980

Max Act: 2.9148. Min Act: -0.0001

Data Index: 654674 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 4.9980. Min Range: -4.9980

Max Act: 2.6475. Min Act: -0.0000

Data Index: 534997 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 4.9980. Min Range: -4.9980

Max Act: 2.9100. Min Act: -0.0001

Data Index: 192037 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 4.9980. Min Range: -4.9980

Max Act: 2.7231. Min Act: -0.0001

Data Index: 732763 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 4.9980. Min Range: -4.9980

Max Act: 3.1858. Min Act: -0.0001

Data Index: 558125 (C4 (Web Text))

Max Activating Token Index: 778