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

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

Neuron 805 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: 0.0135. Min Range: -0.0135

Max Act: 0.0135. Min Act: -0.0004

Data Index: 564255 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0132. Min Act: -0.0003

Data Index: 497771 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0129. Min Act: -0.0003

Data Index: 854027 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0128. Min Act: -0.0004

Data Index: 221447 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0128. Min Act: -0.0003

Data Index: 1196728 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0128. Min Act: -0.0004

Data Index: 592890 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0125. Min Act: -0.0003

Data Index: 1218639 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0130. Min Act: -0.0003

Data Index: 1256624 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0125. Min Act: -0.0003

Data Index: 842297 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0127. Min Act: -0.0003

Data Index: 1150415 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0127. Min Act: -0.0003

Data Index: 245946 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0123. Min Act: -0.0003

Data Index: 236758 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0125. Min Act: -0.0004

Data Index: 280562 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0125. Min Act: -0.0003

Data Index: 832865 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0122. Min Act: -0.0003

Data Index: 153317 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0125. Min Act: -0.0003

Data Index: 1016176 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0121. Min Act: -0.0004

Data Index: 58404 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0123. Min Act: -0.0003

Data Index: 595382 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0123. Min Act: -0.0004

Data Index: 600818 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0123. Min Act: -0.0003

Data Index: 744720 (C4 (Web Text))

Max Activating Token Index: 525