Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 3 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0160. Min Act: -0.0004

Data Index: 141004 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0135. Min Act: -0.0005

Data Index: 364606 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0135. Min Act: -0.0004

Data Index: 810503 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0133. Min Act: -0.0004

Data Index: 963761 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0131. Min Act: -0.0004

Data Index: 1146658 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0130. Min Act: -0.0004

Data Index: 713121 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0126. Min Act: -0.0004

Data Index: 748226 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0121. Min Act: -0.0004

Data Index: 230784 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0122. Min Act: -0.0005

Data Index: 662883 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0120. Min Act: -0.0005

Data Index: 205218 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0121. Min Act: -0.0005

Data Index: 30530 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0118. Min Act: -0.0004

Data Index: 966167 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0116. Min Act: -0.0004

Data Index: 1243121 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0117. Min Act: -0.0004

Data Index: 686398 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0115. Min Act: -0.0004

Data Index: 335665 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0116. Min Act: -0.0004

Data Index: 1341309 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0115. Min Act: -0.0004

Data Index: 1304347 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0113. Min Act: -0.0004

Data Index: 71720 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0112. Min Act: -0.0004

Data Index: 270318 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0112. Min Act: -0.0005

Data Index: 1050064 (C4 (Web Text))

Max Activating Token Index: 128