Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 657 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0119. Min Act: -0.0005

Data Index: 326978 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0118. Min Act: -0.0005

Data Index: 763684 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0114. Min Act: -0.0005

Data Index: 469245 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0112. Min Act: -0.0005

Data Index: 1455776 (Python Code)

Max Activating Token Index: 476

Text #4

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0112. Min Act: -0.0005

Data Index: 1635424 (Python Code)

Max Activating Token Index: 373

Text #5

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0109. Min Act: -0.0005

Data Index: 1251091 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0110. Min Act: -0.0005

Data Index: 1342022 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0108. Min Act: -0.0006

Data Index: 550761 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0109. Min Act: -0.0005

Data Index: 293385 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0108. Min Act: -0.0005

Data Index: 373912 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0106. Min Act: -0.0005

Data Index: 187826 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0107. Min Act: -0.0005

Data Index: 84134 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0106. Min Act: -0.0005

Data Index: 802400 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0102. Min Act: -0.0005

Data Index: 1380647 (Python Code)

Max Activating Token Index: 817

Text #14

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1046325 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0106. Min Act: -0.0005

Data Index: 1244956 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0105. Min Act: -0.0005

Data Index: 967979 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0103. Min Act: -0.0005

Data Index: 1391408 (Python Code)

Max Activating Token Index: 169

Text #18

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0103. Min Act: -0.0005

Data Index: 767405 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.0119. Min Range: -0.0119

Max Act: 0.0103. Min Act: -0.0005

Data Index: 457614 (C4 (Web Text))

Max Activating Token Index: 546