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

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

Neuron 5705 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: 0.1302. Min Range: -0.1302

Max Act: 0.1302. Min Act: -0.0001

Data Index: 639567 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1060. Min Act: -0.0001

Data Index: 821226 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1065. Min Act: -0.0001

Data Index: 734967 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1052. Min Act: -0.0001

Data Index: 227258 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1033. Min Act: -0.0001

Data Index: 285452 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1071. Min Act: -0.0001

Data Index: 688495 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1037. Min Act: -0.0001

Data Index: 758956 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1001. Min Act: -0.0001

Data Index: 516576 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1003. Min Act: -0.0001

Data Index: 1313099 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1017. Min Act: -0.0001

Data Index: 865546 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1001. Min Act: -0.0001

Data Index: 296231 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0979. Min Act: -0.0001

Data Index: 412391 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0986. Min Act: -0.0001

Data Index: 196778 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1113060 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0961. Min Act: -0.0001

Data Index: 867200 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0962. Min Act: -0.0001

Data Index: 459976 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1123054 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0957. Min Act: -0.0001

Data Index: 531933 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1309155 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0935. Min Act: -0.0001

Data Index: 40170 (C4 (Web Text))

Max Activating Token Index: 761