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

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

Neuron 1421 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3538. Min Act: -0.0001

Data Index: 317539 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3766. Min Act: -0.0001

Data Index: 435566 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3818. Min Act: -0.0001

Data Index: 419901 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3774. Min Act: -0.0001

Data Index: 1177752 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3440. Min Act: -0.0001

Data Index: 74144 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3423. Min Act: -0.0001

Data Index: 678335 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3544. Min Act: -0.0001

Data Index: 733028 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3496. Min Act: -0.0001

Data Index: 14427 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3217. Min Act: -0.0001

Data Index: 1039526 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3316. Min Act: -0.0001

Data Index: 1108164 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3283. Min Act: -0.0001

Data Index: 1072984 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3146. Min Act: -0.0001

Data Index: 823685 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3227. Min Act: -0.0001

Data Index: 1179065 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3103. Min Act: -0.0001

Data Index: 1117938 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3020. Min Act: -0.0001

Data Index: 723074 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3045. Min Act: -0.0001

Data Index: 896813 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3243. Min Act: -0.0001

Data Index: 409204 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3106. Min Act: -0.0001

Data Index: 950558 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3112. Min Act: -0.0001

Data Index: 33983 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3075. Min Act: -0.0001

Data Index: 997019 (C4 (Web Text))

Max Activating Token Index: 636