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

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

Neuron 2140 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0153. Min Act: -0.0004

Data Index: 19416 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0143. Min Act: -0.0003

Data Index: 72324 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0143. Min Act: -0.0003

Data Index: 88557 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0142. Min Act: -0.0003

Data Index: 1285561 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0141. Min Act: -0.0003

Data Index: 418972 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0139. Min Act: -0.0003

Data Index: 333261 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0141. Min Act: -0.0003

Data Index: 1164307 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0141. Min Act: -0.0003

Data Index: 867323 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0141. Min Act: -0.0003

Data Index: 501603 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0141. Min Act: -0.0003

Data Index: 541948 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0140. Min Act: -0.0003

Data Index: 1203426 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0136. Min Act: -0.0003

Data Index: 332690 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0135. Min Act: -0.0003

Data Index: 653453 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0130. Min Act: -0.0003

Data Index: 1349606 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0132. Min Act: -0.0003

Data Index: 95619 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0131. Min Act: -0.0003

Data Index: 572038 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0130. Min Act: -0.0003

Data Index: 1056487 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0131. Min Act: -0.0003

Data Index: 396309 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0125. Min Act: -0.0004

Data Index: 1096169 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0127. Min Act: -0.0003

Data Index: 500815 (C4 (Web Text))

Max Activating Token Index: 902