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

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

Neuron 581 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: 0.0175. Min Range: -0.0175

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1238920 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0152. Min Act: -0.0006

Data Index: 449019 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0149. Min Act: -0.0006

Data Index: 925036 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0152. Min Act: -0.0005

Data Index: 302030 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0151. Min Act: -0.0006

Data Index: 221477 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1337804 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0144. Min Act: -0.0005

Data Index: 324985 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0128. Min Act: -0.0005

Data Index: 1645275 (Python Code)

Max Activating Token Index: 239

Text #8

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0142. Min Act: -0.0006

Data Index: 363030 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0141. Min Act: -0.0005

Data Index: 116335 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0154. Min Act: -0.0005

Data Index: 436093 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0133. Min Act: -0.0006

Data Index: 994336 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0121. Min Act: -0.0006

Data Index: 191329 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0144. Min Act: -0.0005

Data Index: 896478 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0108. Min Act: -0.0005

Data Index: 838231 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1123465 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0127. Min Act: -0.0006

Data Index: 1450758 (Python Code)

Max Activating Token Index: 50

Text #17

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1394951 (Python Code)

Max Activating Token Index: 607

Text #18

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0124. Min Act: -0.0006

Data Index: 658328 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0119. Min Act: -0.0006

Data Index: 1297181 (C4 (Web Text))

Max Activating Token Index: 368