Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 848 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0143. Min Act: -0.0004

Data Index: 1656632 (Python Code)

Max Activating Token Index: 918

Text #1

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0143. Min Act: -0.0004

Data Index: 120745 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0142. Min Act: -0.0004

Data Index: 12847 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0141. Min Act: -0.0004

Data Index: 554111 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0133. Min Act: -0.0004

Data Index: 824943 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0139. Min Act: -0.0004

Data Index: 1348597 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0131. Min Act: -0.0004

Data Index: 1617449 (Python Code)

Max Activating Token Index: 17

Text #7

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0133. Min Act: -0.0004

Data Index: 1566149 (Python Code)

Max Activating Token Index: 763

Text #8

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0130. Min Act: -0.0004

Data Index: 1197725 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0133. Min Act: -0.0004

Data Index: 1096900 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0138. Min Act: -0.0004

Data Index: 41235 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0126. Min Act: -0.0004

Data Index: 725323 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0125. Min Act: -0.0004

Data Index: 235206 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0130. Min Act: -0.0004

Data Index: 1111633 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0126. Min Act: -0.0004

Data Index: 1186705 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0129. Min Act: -0.0004

Data Index: 179939 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0125. Min Act: -0.0004

Data Index: 738728 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0130. Min Act: -0.0004

Data Index: 627051 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0104. Min Act: -0.0004

Data Index: 343605 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0122. Min Act: -0.0004

Data Index: 243436 (C4 (Web Text))

Max Activating Token Index: 309