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

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

Neuron 348 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0144. Min Act: -0.0006

Data Index: 413456 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0143. Min Act: -0.0006

Data Index: 493328 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1016477 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0139. Min Act: -0.0006

Data Index: 392889 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1025307 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1172415 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0135. Min Act: -0.0006

Data Index: 105979 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0130. Min Act: -0.0006

Data Index: 452114 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1349664 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0129. Min Act: -0.0006

Data Index: 384642 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0130. Min Act: -0.0006

Data Index: 648123 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0129. Min Act: -0.0006

Data Index: 189669 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0125. Min Act: -0.0006

Data Index: 798570 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0128. Min Act: -0.0006

Data Index: 433207 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0127. Min Act: -0.0006

Data Index: 330740 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0127. Min Act: -0.0006

Data Index: 988745 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0127. Min Act: -0.0006

Data Index: 65866 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0125. Min Act: -0.0006

Data Index: 269453 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0127. Min Act: -0.0006

Data Index: 1223803 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0124. Min Act: -0.0006

Data Index: 630207 (C4 (Web Text))

Max Activating Token Index: 640