Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1629 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.1064. Min Act: -0.0003

Data Index: 1204582 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.1025. Min Act: -0.0003

Data Index: 226049 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0989. Min Act: -0.0003

Data Index: 492509 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.1046. Min Act: -0.0003

Data Index: 507991 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0965. Min Act: -0.0003

Data Index: 441155 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.1009. Min Act: -0.0003

Data Index: 989167 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0932. Min Act: -0.0003

Data Index: 465129 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0938. Min Act: -0.0003

Data Index: 452431 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0938. Min Act: -0.0003

Data Index: 712944 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0904. Min Act: -0.0003

Data Index: 1223523 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0910. Min Act: -0.0002

Data Index: 914197 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0920. Min Act: -0.0003

Data Index: 1226202 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0951. Min Act: -0.0003

Data Index: 976495 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0910. Min Act: -0.0003

Data Index: 380028 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0886. Min Act: -0.0003

Data Index: 1153576 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0919. Min Act: -0.0003

Data Index: 500865 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0874. Min Act: -0.0002

Data Index: 519350 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0956. Min Act: -0.0003

Data Index: 536623 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0897. Min Act: -0.0003

Data Index: 1116455 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0900. Min Act: -0.0003

Data Index: 197649 (C4 (Web Text))

Max Activating Token Index: 425