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

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

Neuron 1552 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4773. Min Range: -4.4773

Max Act: 4.4773. Min Act: -0.0001

Data Index: 890553 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 4.4773. Min Range: -4.4773

Max Act: 4.4581. Min Act: -0.0001

Data Index: 492233 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 4.4773. Min Range: -4.4773

Max Act: 4.4728. Min Act: -0.0001

Data Index: 993503 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 4.4773. Min Range: -4.4773

Max Act: 4.1251. Min Act: -0.0001

Data Index: 1309865 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 4.4773. Min Range: -4.4773

Max Act: 3.7724. Min Act: -0.0001

Data Index: 897688 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 4.4773. Min Range: -4.4773

Max Act: 3.4339. Min Act: -0.0001

Data Index: 340012 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 4.4773. Min Range: -4.4773

Max Act: 3.8749. Min Act: -0.0001

Data Index: 187563 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 4.4773. Min Range: -4.4773

Max Act: 3.7120. Min Act: -0.0001

Data Index: 964458 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 4.4773. Min Range: -4.4773

Max Act: 3.6760. Min Act: -0.0001

Data Index: 1164251 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 4.4773. Min Range: -4.4773

Max Act: 3.6691. Min Act: -0.0001

Data Index: 592569 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 4.4773. Min Range: -4.4773

Max Act: 4.1188. Min Act: -0.0001

Data Index: 1063353 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 4.4773. Min Range: -4.4773

Max Act: 3.6730. Min Act: -0.0001

Data Index: 645052 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 4.4773. Min Range: -4.4773

Max Act: 3.1827. Min Act: -0.0001

Data Index: 1100111 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 4.4773. Min Range: -4.4773

Max Act: 3.9141. Min Act: -0.0001

Data Index: 329660 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 4.4773. Min Range: -4.4773

Max Act: 3.7447. Min Act: -0.0001

Data Index: 290006 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 4.4773. Min Range: -4.4773

Max Act: 3.4370. Min Act: -0.0001

Data Index: 745542 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 4.4773. Min Range: -4.4773

Max Act: 2.6703. Min Act: -0.0001

Data Index: 390452 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 4.4773. Min Range: -4.4773

Max Act: 3.6043. Min Act: -0.0001

Data Index: 865780 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 4.4773. Min Range: -4.4773

Max Act: 3.7497. Min Act: -0.0001

Data Index: 839191 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 4.4773. Min Range: -4.4773

Max Act: 3.7392. Min Act: -0.0001

Data Index: 135150 (C4 (Web Text))

Max Activating Token Index: 337