Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 685 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.6064. Min Act: -0.0001

Data Index: 1135298 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5940. Min Act: -0.0001

Data Index: 770400 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5979. Min Act: -0.0001

Data Index: 1024780 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5449. Min Act: -0.0001

Data Index: 686989 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5493. Min Act: -0.0001

Data Index: 1158223 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5896. Min Act: -0.0001

Data Index: 871102 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5421. Min Act: -0.0001

Data Index: 982423 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5341. Min Act: -0.0001

Data Index: 612103 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5191. Min Act: -0.0001

Data Index: 1111563 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5305. Min Act: -0.0001

Data Index: 809969 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5093. Min Act: -0.0001

Data Index: 405222 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4676. Min Act: -0.0001

Data Index: 965610 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4679. Min Act: -0.0001

Data Index: 854377 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.5348. Min Act: -0.0001

Data Index: 206708 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4989. Min Act: -0.0001

Data Index: 1022338 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4794. Min Act: -0.0001

Data Index: 66320 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4879. Min Act: -0.0001

Data Index: 290626 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4715. Min Act: -0.0001

Data Index: 123027 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4655. Min Act: -0.0001

Data Index: 40154 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.6064. Min Range: -0.6064

Max Act: 0.4666. Min Act: -0.0001

Data Index: 351569 (C4 (Web Text))

Max Activating Token Index: 196