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

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

Neuron 1726 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: 0.0155. Min Range: -0.0155

Max Act: 0.0155. Min Act: -0.0006

Data Index: 193712 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0147. Min Act: -0.0006

Data Index: 137619 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0145. Min Act: -0.0006

Data Index: 1320391 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0144. Min Act: -0.0006

Data Index: 765406 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0143. Min Act: -0.0006

Data Index: 666531 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0139. Min Act: -0.0006

Data Index: 73518 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0142. Min Act: -0.0006

Data Index: 1222403 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0139. Min Act: -0.0006

Data Index: 9008 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0138. Min Act: -0.0006

Data Index: 488559 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0137. Min Act: -0.0006

Data Index: 537906 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1022162 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1149711 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1218241 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0134. Min Act: -0.0005

Data Index: 1422165 (Python Code)

Max Activating Token Index: 63

Text #14

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1253649 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0130. Min Act: -0.0006

Data Index: 246456 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1349305 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0130. Min Act: -0.0006

Data Index: 1383979 (Python Code)

Max Activating Token Index: 893

Text #18

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0133. Min Act: -0.0006

Data Index: 64078 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0132. Min Act: -0.0006

Data Index: 782776 (C4 (Web Text))

Max Activating Token Index: 236