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

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

Neuron 4503 in Layer 1

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: 0.1939. Min Range: -0.1939

Max Act: 0.1939. Min Act: -0.0002

Data Index: 1287801 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1890. Min Act: -0.0002

Data Index: 1233351 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1898. Min Act: -0.0002

Data Index: 352476 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1751. Min Act: -0.0002

Data Index: 1051314 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1796. Min Act: -0.0002

Data Index: 364908 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1723. Min Act: -0.0002

Data Index: 420076 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1748. Min Act: -0.0002

Data Index: 661614 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1686. Min Act: -0.0003

Data Index: 270915 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1668. Min Act: -0.0002

Data Index: 347059 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1638. Min Act: -0.0002

Data Index: 891351 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1698. Min Act: -0.0002

Data Index: 638842 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1699. Min Act: -0.0002

Data Index: 687810 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1636. Min Act: -0.0002

Data Index: 779881 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1570. Min Act: -0.0002

Data Index: 264943 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1552. Min Act: -0.0002

Data Index: 998237 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1551. Min Act: -0.0002

Data Index: 50685 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1552. Min Act: -0.0002

Data Index: 1145508 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1515. Min Act: -0.0002

Data Index: 293311 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1549. Min Act: -0.0002

Data Index: 76134 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1508. Min Act: -0.0002

Data Index: 950347 (C4 (Web Text))

Max Activating Token Index: 126