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

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

Neuron 1503 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: 0.0173. Min Range: -0.0173

Max Act: 0.0173. Min Act: -0.0006

Data Index: 480261 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0163. Min Act: -0.0006

Data Index: 370314 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0152. Min Act: -0.0006

Data Index: 607705 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0159. Min Act: -0.0006

Data Index: 772880 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0151. Min Act: -0.0006

Data Index: 178601 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0152. Min Act: -0.0005

Data Index: 634759 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0151. Min Act: -0.0006

Data Index: 780307 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0146. Min Act: -0.0006

Data Index: 148280 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0145. Min Act: -0.0005

Data Index: 455686 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0144. Min Act: -0.0006

Data Index: 710706 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0142. Min Act: -0.0006

Data Index: 390198 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0142. Min Act: -0.0006

Data Index: 998444 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0145. Min Act: -0.0005

Data Index: 1093108 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0138. Min Act: -0.0006

Data Index: 764361 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0137. Min Act: -0.0006

Data Index: 705110 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0140. Min Act: -0.0006

Data Index: 988392 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1174198 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1465069 (Python Code)

Max Activating Token Index: 30

Text #18

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1133551 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1331863 (C4 (Web Text))

Max Activating Token Index: 42