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

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

Neuron 1406 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0152. Min Act: -0.0006

Data Index: 15155 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0153. Min Act: -0.0006

Data Index: 42739 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0138. Min Act: -0.0006

Data Index: 325511 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0139. Min Act: -0.0006

Data Index: 847090 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0135. Min Act: -0.0006

Data Index: 161033 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1107619 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0138. Min Act: -0.0006

Data Index: 931971 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0135. Min Act: -0.0006

Data Index: 642161 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0141. Min Act: -0.0006

Data Index: 1189137 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0127. Min Act: -0.0006

Data Index: 981164 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1206368 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0134. Min Act: -0.0006

Data Index: 737760 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0131. Min Act: -0.0006

Data Index: 990412 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0131. Min Act: -0.0006

Data Index: 363957 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0129. Min Act: -0.0006

Data Index: 422355 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0128. Min Act: -0.0006

Data Index: 342299 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0131. Min Act: -0.0006

Data Index: 849364 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0127. Min Act: -0.0006

Data Index: 555840 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1130714 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0120. Min Act: -0.0006

Data Index: 25996 (C4 (Web Text))

Max Activating Token Index: 80