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

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

Neuron 1310 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: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0003

Data Index: 649031 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0160. Min Act: -0.0003

Data Index: 623383 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0151. Min Act: -0.0004

Data Index: 1329380 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0151. Min Act: -0.0003

Data Index: 633227 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0147. Min Act: -0.0003

Data Index: 370997 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0146. Min Act: -0.0003

Data Index: 1208687 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0145. Min Act: -0.0004

Data Index: 579670 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0142. Min Act: -0.0004

Data Index: 1280747 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0142. Min Act: -0.0004

Data Index: 1135419 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0136. Min Act: -0.0003

Data Index: 474015 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0135. Min Act: -0.0003

Data Index: 1245498 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0132. Min Act: -0.0003

Data Index: 516646 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0133. Min Act: -0.0004

Data Index: 502443 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0132. Min Act: -0.0004

Data Index: 213529 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0130. Min Act: -0.0003

Data Index: 664481 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0131. Min Act: -0.0003

Data Index: 649270 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0128. Min Act: -0.0004

Data Index: 781755 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0128. Min Act: -0.0003

Data Index: 445028 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0127. Min Act: -0.0003

Data Index: 758816 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0127. Min Act: -0.0003

Data Index: 1069399 (C4 (Web Text))

Max Activating Token Index: 100