Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 597 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0150. Min Act: -0.0006

Data Index: 733633 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0143. Min Act: -0.0006

Data Index: 127984 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0141. Min Act: -0.0006

Data Index: 308175 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0142. Min Act: -0.0006

Data Index: 853822 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0141. Min Act: -0.0006

Data Index: 646857 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0139. Min Act: -0.0006

Data Index: 928323 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1342037 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1318293 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0139. Min Act: -0.0006

Data Index: 942889 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0138. Min Act: -0.0006

Data Index: 167102 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1017894 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0135. Min Act: -0.0006

Data Index: 890008 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0138. Min Act: -0.0006

Data Index: 187317 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1258393 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0134. Min Act: -0.0006

Data Index: 739732 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0133. Min Act: -0.0006

Data Index: 56560 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0135. Min Act: -0.0006

Data Index: 701177 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1148866 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0133. Min Act: -0.0006

Data Index: 924586 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.0150. Min Range: -0.0150

Max Act: 0.0132. Min Act: -0.0006

Data Index: 482467 (C4 (Web Text))

Max Activating Token Index: 1023