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

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

Neuron 1504 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0047. Min Act: -0.0003

Data Index: 168074 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0048. Min Act: -0.0003

Data Index: 92634 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1656820 (Python Code)

Max Activating Token Index: 763

Text #3

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0043. Min Act: -0.0003

Data Index: 923949 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0046. Min Act: -0.0003

Data Index: 1225306 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0046. Min Act: -0.0003

Data Index: 326464 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0043. Min Act: -0.0003

Data Index: 922080 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0040. Min Act: -0.0003

Data Index: 406870 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0043. Min Act: -0.0004

Data Index: 749432 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0041. Min Act: -0.0003

Data Index: 1124352 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0042. Min Act: -0.0003

Data Index: 698656 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0040. Min Act: -0.0003

Data Index: 179265 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0040. Min Act: -0.0004

Data Index: 415341 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0043. Min Act: -0.0003

Data Index: 457066 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0043. Min Act: -0.0003

Data Index: 356312 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0043. Min Act: -0.0003

Data Index: 696949 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0038. Min Act: -0.0003

Data Index: 418633 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0037. Min Act: -0.0003

Data Index: 1484669 (Python Code)

Max Activating Token Index: 233

Text #18

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0041. Min Act: -0.0003

Data Index: 1457492 (Python Code)

Max Activating Token Index: 55

Text #19

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0032. Min Act: -0.0003

Data Index: 1640232 (Python Code)

Max Activating Token Index: 878