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

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

Neuron 2686 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0064. Min Act: -0.0002

Data Index: 1513023 (Python Code)

Max Activating Token Index: 222

Text #1

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1302240 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0003

Data Index: 622675 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1375211 (Python Code)

Max Activating Token Index: 30

Text #4

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1321420 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0057. Min Act: -0.0003

Data Index: 371877 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0057. Min Act: -0.0003

Data Index: 969706 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1514562 (Python Code)

Max Activating Token Index: 152

Text #8

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0056. Min Act: -0.0003

Data Index: 666430 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0056. Min Act: -0.0003

Data Index: 1051083 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1631299 (Python Code)

Max Activating Token Index: 210

Text #11

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0055. Min Act: -0.0003

Data Index: 894186 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1557945 (Python Code)

Max Activating Token Index: 894

Text #13

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1508537 (Python Code)

Max Activating Token Index: 70

Text #14

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0054. Min Act: -0.0003

Data Index: 272962 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1444390 (Python Code)

Max Activating Token Index: 447

Text #16

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1404534 (Python Code)

Max Activating Token Index: 205

Text #17

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0054. Min Act: -0.0003

Data Index: 224333 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0054. Min Act: -0.0003

Data Index: 17073 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1522583 (Python Code)

Max Activating Token Index: 571