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

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

Neuron 3714 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: 0.2814. Min Range: -0.2814

Max Act: 0.2814. Min Act: -0.0001

Data Index: 1513218 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2546. Min Act: -0.0001

Data Index: 1385952 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2549. Min Act: -0.0001

Data Index: 1474244 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2476. Min Act: -0.0001

Data Index: 1625184 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2491. Min Act: -0.0001

Data Index: 1523766 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2412. Min Act: -0.0001

Data Index: 1567116 (Python Code)

Max Activating Token Index: 567

Text #6

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2339. Min Act: -0.0001

Data Index: 1639044 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2360. Min Act: -0.0001

Data Index: 1435655 (Python Code)

Max Activating Token Index: 74

Text #8

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2223. Min Act: -0.0001

Data Index: 1534851 (Python Code)

Max Activating Token Index: 580

Text #9

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2203. Min Act: -0.0001

Data Index: 1511181 (Python Code)

Max Activating Token Index: 107

Text #10

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2148. Min Act: -0.0001

Data Index: 1381895 (Python Code)

Max Activating Token Index: 118

Text #11

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2154. Min Act: -0.0001

Data Index: 1418700 (Python Code)

Max Activating Token Index: 352

Text #12

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2149. Min Act: -0.0001

Data Index: 1570017 (Python Code)

Max Activating Token Index: 219

Text #13

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2079. Min Act: -0.0001

Data Index: 1637374 (Python Code)

Max Activating Token Index: 54

Text #14

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2119. Min Act: -0.0001

Data Index: 1387762 (Python Code)

Max Activating Token Index: 69

Text #15

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2074. Min Act: -0.0001

Data Index: 1512663 (Python Code)

Max Activating Token Index: 18

Text #16

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2101. Min Act: -0.0001

Data Index: 1485800 (Python Code)

Max Activating Token Index: 116

Text #17

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2089. Min Act: -0.0001

Data Index: 1413237 (Python Code)

Max Activating Token Index: 478

Text #18

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2053. Min Act: -0.0001

Data Index: 1508718 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2048. Min Act: -0.0001

Data Index: 1447467 (Python Code)

Max Activating Token Index: 97