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

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

Neuron 112 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: 1.6258. Min Range: -1.6258

Max Act: 1.6258. Min Act: -0.0002

Data Index: 99642 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 1.6258. Min Range: -1.6258

Max Act: 1.5085. Min Act: -0.0002

Data Index: 419476 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 1.6258. Min Range: -1.6258

Max Act: 1.4736. Min Act: -0.0002

Data Index: 203653 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 1.6258. Min Range: -1.6258

Max Act: 1.3590. Min Act: -0.0002

Data Index: 25068 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 1.6258. Min Range: -1.6258

Max Act: 1.3356. Min Act: -0.0002

Data Index: 738451 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 1.6258. Min Range: -1.6258

Max Act: 1.3255. Min Act: -0.0002

Data Index: 220168 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 1.6258. Min Range: -1.6258

Max Act: 1.3361. Min Act: -0.0002

Data Index: 13066 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 1.6258. Min Range: -1.6258

Max Act: 1.3049. Min Act: -0.0002

Data Index: 1077838 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 1.6258. Min Range: -1.6258

Max Act: 1.3331. Min Act: -0.0002

Data Index: 1020985 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 1.6258. Min Range: -1.6258

Max Act: 1.3667. Min Act: -0.0002

Data Index: 1222933 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 1.6258. Min Range: -1.6258

Max Act: 1.2880. Min Act: -0.0002

Data Index: 270238 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 1.6258. Min Range: -1.6258

Max Act: 1.2916. Min Act: -0.0002

Data Index: 568983 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 1.6258. Min Range: -1.6258

Max Act: 1.2783. Min Act: -0.0002

Data Index: 707072 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 1.6258. Min Range: -1.6258

Max Act: 1.2647. Min Act: -0.0002

Data Index: 371084 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 1.6258. Min Range: -1.6258

Max Act: 1.2850. Min Act: -0.0002

Data Index: 869829 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 1.6258. Min Range: -1.6258

Max Act: 1.2500. Min Act: -0.0002

Data Index: 444 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 1.6258. Min Range: -1.6258

Max Act: 1.2931. Min Act: -0.0002

Data Index: 1297377 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 1.6258. Min Range: -1.6258

Max Act: 1.2708. Min Act: -0.0002

Data Index: 1317135 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 1.6258. Min Range: -1.6258

Max Act: 1.2598. Min Act: -0.0002

Data Index: 126481 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 1.6258. Min Range: -1.6258

Max Act: 1.2638. Min Act: -0.0002

Data Index: 916626 (C4 (Web Text))

Max Activating Token Index: 647