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

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

Neuron 1106 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: 0.0173. Min Range: -0.0173

Max Act: 0.0173. Min Act: -0.0006

Data Index: 116648 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0130. Min Act: -0.0006

Data Index: 1187029 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0130. Min Act: -0.0006

Data Index: 650667 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0132. Min Act: -0.0006

Data Index: 211493 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0131. Min Act: -0.0006

Data Index: 191255 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0127. Min Act: -0.0006

Data Index: 400896 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0126. Min Act: -0.0006

Data Index: 611689 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1000996 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0125. Min Act: -0.0006

Data Index: 65896 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0122. Min Act: -0.0006

Data Index: 106228 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0125. Min Act: -0.0006

Data Index: 860185 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0126. Min Act: -0.0006

Data Index: 586445 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1034142 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0123. Min Act: -0.0006

Data Index: 610260 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0120. Min Act: -0.0006

Data Index: 532408 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0122. Min Act: -0.0006

Data Index: 592666 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1107690 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0118. Min Act: -0.0006

Data Index: 457234 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0123. Min Act: -0.0006

Data Index: 658084 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1232400 (C4 (Web Text))

Max Activating Token Index: 817