Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1176 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0165. Min Act: -0.0003

Data Index: 373998 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1579172 (Python Code)

Max Activating Token Index: 352

Text #2

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0156. Min Act: -0.0003

Data Index: 1436488 (Python Code)

Max Activating Token Index: 677

Text #3

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0154. Min Act: -0.0003

Data Index: 78470 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0155. Min Act: -0.0003

Data Index: 1368230 (Python Code)

Max Activating Token Index: 833

Text #5

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0141. Min Act: -0.0003

Data Index: 1614638 (Python Code)

Max Activating Token Index: 578

Text #6

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0141. Min Act: -0.0003

Data Index: 876915 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0137. Min Act: -0.0003

Data Index: 1160564 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0137. Min Act: -0.0003

Data Index: 491408 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0136. Min Act: -0.0003

Data Index: 432730 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0136. Min Act: -0.0003

Data Index: 800812 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0137. Min Act: -0.0003

Data Index: 592170 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0133. Min Act: -0.0002

Data Index: 455532 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0133. Min Act: -0.0003

Data Index: 1123849 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0132. Min Act: -0.0003

Data Index: 1637278 (Python Code)

Max Activating Token Index: 810

Text #15

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0132. Min Act: -0.0003

Data Index: 714746 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0131. Min Act: -0.0003

Data Index: 521962 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0131. Min Act: -0.0003

Data Index: 937314 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0130. Min Act: -0.0003

Data Index: 878580 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0132. Min Act: -0.0003

Data Index: 827467 (C4 (Web Text))

Max Activating Token Index: 539