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

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

Neuron 172 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: 0.0186. Min Range: -0.0186

Max Act: 0.0186. Min Act: -0.0006

Data Index: 767778 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0153. Min Act: -0.0006

Data Index: 852954 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0148. Min Act: -0.0006

Data Index: 599270 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1185009 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0145. Min Act: -0.0006

Data Index: 1085512 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0138. Min Act: -0.0006

Data Index: 774134 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0140. Min Act: -0.0006

Data Index: 264969 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1188401 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1217165 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0136. Min Act: -0.0006

Data Index: 841799 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1011662 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0140. Min Act: -0.0005

Data Index: 1279065 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0137. Min Act: -0.0006

Data Index: 788255 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0137. Min Act: -0.0006

Data Index: 799551 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0136. Min Act: -0.0005

Data Index: 607540 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1176044 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0129. Min Act: -0.0006

Data Index: 138878 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0131. Min Act: -0.0006

Data Index: 456770 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1190059 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1144742 (C4 (Web Text))

Max Activating Token Index: 893