Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1904 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0001

Data Index: 208260 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0161. Min Act: -0.0001

Data Index: 1277916 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0157. Min Act: -0.0001

Data Index: 9995 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0131. Min Act: -0.0001

Data Index: 1242241 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0127. Min Act: -0.0001

Data Index: 1606816 (Python Code)

Max Activating Token Index: 171

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0123. Min Act: -0.0001

Data Index: 696916 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0116. Min Act: -0.0001

Data Index: 735429 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0115. Min Act: -0.0001

Data Index: 1257371 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0115. Min Act: -0.0002

Data Index: 652532 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0113. Min Act: -0.0001

Data Index: 801785 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1233838 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0111. Min Act: -0.0001

Data Index: 1095260 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0111. Min Act: -0.0001

Data Index: 726895 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0108. Min Act: -0.0001

Data Index: 20800 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0104. Min Act: -0.0001

Data Index: 502983 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0103. Min Act: -0.0001

Data Index: 1567515 (Python Code)

Max Activating Token Index: 199

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0104. Min Act: -0.0001

Data Index: 167835 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0101. Min Act: -0.0001

Data Index: 1224244 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0101. Min Act: -0.0001

Data Index: 73504 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0100. Min Act: -0.0001

Data Index: 768035 (C4 (Web Text))

Max Activating Token Index: 26