Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 153 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0150. Min Act: -0.0005

Data Index: 1089783 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0155. Min Act: -0.0005

Data Index: 813033 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0137. Min Act: -0.0006

Data Index: 1387759 (Python Code)

Max Activating Token Index: 457

Text #3

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0166. Min Act: -0.0006

Data Index: 1267067 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0155. Min Act: -0.0006

Data Index: 485756 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0166. Min Act: -0.0006

Data Index: 472057 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0161. Min Act: -0.0006

Data Index: 488770 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1604510 (Python Code)

Max Activating Token Index: 628

Text #8

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0158. Min Act: -0.0006

Data Index: 1566399 (Python Code)

Max Activating Token Index: 207

Text #9

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0158. Min Act: -0.0006

Data Index: 1508657 (Python Code)

Max Activating Token Index: 716

Text #10

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0167. Min Act: -0.0005

Data Index: 621074 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0156. Min Act: -0.0005

Data Index: 843268 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0155. Min Act: -0.0006

Data Index: 289473 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0158. Min Act: -0.0006

Data Index: 1623077 (Python Code)

Max Activating Token Index: 178

Text #14

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0119. Min Act: -0.0006

Data Index: 684050 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0139. Min Act: -0.0006

Data Index: 77612 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0148. Min Act: -0.0005

Data Index: 46793 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0159. Min Act: -0.0006

Data Index: 346818 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0151. Min Act: -0.0006

Data Index: 1652088 (Python Code)

Max Activating Token Index: 968

Text #19

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0155. Min Act: -0.0006

Data Index: 942448 (C4 (Web Text))

Max Activating Token Index: 373