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

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

Neuron 1051 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0277. Min Act: -0.0005

Data Index: 1372470 (Python Code)

Max Activating Token Index: 250

Text #1

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0223. Min Act: -0.0006

Data Index: 229849 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1323574 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0167. Min Act: -0.0006

Data Index: 157390 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0158. Min Act: -0.0005

Data Index: 1423316 (Python Code)

Max Activating Token Index: 36

Text #5

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1075609 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1317486 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0127. Min Act: -0.0005

Data Index: 1586150 (Python Code)

Max Activating Token Index: 68

Text #8

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0126. Min Act: -0.0005

Data Index: 1557260 (Python Code)

Max Activating Token Index: 54

Text #9

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0126. Min Act: -0.0005

Data Index: 1609525 (Python Code)

Max Activating Token Index: 58

Text #10

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1049527 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0116. Min Act: -0.0005

Data Index: 1461566 (Python Code)

Max Activating Token Index: 366

Text #12

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0115. Min Act: -0.0006

Data Index: 484617 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0116. Min Act: -0.0005

Data Index: 1572046 (Python Code)

Max Activating Token Index: 252

Text #14

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1524037 (Python Code)

Max Activating Token Index: 924

Text #15

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0112. Min Act: -0.0006

Data Index: 61990 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0110. Min Act: -0.0006

Data Index: 694225 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0112. Min Act: -0.0006

Data Index: 241657 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0109. Min Act: -0.0005

Data Index: 1591316 (Python Code)

Max Activating Token Index: 284

Text #19

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0105. Min Act: -0.0005

Data Index: 1605550 (Python Code)

Max Activating Token Index: 374