Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4371 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0157. Min Act: -0.0001

Data Index: 938218 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0156. Min Act: -0.0001

Data Index: 735073 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0147. Min Act: -0.0001

Data Index: 166558 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0150. Min Act: -0.0001

Data Index: 263875 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0145. Min Act: -0.0001

Data Index: 482104 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0145. Min Act: -0.0001

Data Index: 1282310 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0144. Min Act: -0.0001

Data Index: 528949 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0143. Min Act: -0.0001

Data Index: 447240 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0142. Min Act: -0.0001

Data Index: 288722 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0143. Min Act: -0.0001

Data Index: 344613 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0144. Min Act: -0.0001

Data Index: 1137525 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0141. Min Act: -0.0001

Data Index: 746854 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0143. Min Act: -0.0001

Data Index: 860873 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0141. Min Act: -0.0001

Data Index: 1327924 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0141. Min Act: -0.0001

Data Index: 67089 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0140. Min Act: -0.0001

Data Index: 1405064 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0140. Min Act: -0.0001

Data Index: 821877 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0141. Min Act: -0.0001

Data Index: 597907 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0141. Min Act: -0.0001

Data Index: 22241 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0141. Min Act: -0.0001

Data Index: 1344854 (C4 (Web Text))

Max Activating Token Index: 638