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

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

Neuron 5492 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: 0.1300. Min Range: -0.1300

Max Act: 0.1300. Min Act: -0.0001

Data Index: 995684 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1287213 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1212. Min Act: -0.0001

Data Index: 299159 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1189. Min Act: -0.0001

Data Index: 840263 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1212. Min Act: -0.0001

Data Index: 1002574 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1183. Min Act: -0.0001

Data Index: 372819 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1181. Min Act: -0.0001

Data Index: 783684 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1171. Min Act: -0.0001

Data Index: 557558 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1413501 (Python Code)

Max Activating Token Index: 13

Text #9

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1163. Min Act: -0.0001

Data Index: 146487 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1166. Min Act: -0.0001

Data Index: 670333 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1167. Min Act: -0.0001

Data Index: 371678 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1146. Min Act: -0.0001

Data Index: 29500 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1133. Min Act: -0.0001

Data Index: 257310 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1142. Min Act: -0.0001

Data Index: 531744 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1049494 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1074092 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1137. Min Act: -0.0001

Data Index: 20240 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1134. Min Act: -0.0001

Data Index: 1299478 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1135. Min Act: -0.0001

Data Index: 1082484 (C4 (Web Text))

Max Activating Token Index: 670