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

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

Neuron 4273 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: 0.4065. Min Range: -0.4065

Max Act: 0.3942. Min Act: -0.0001

Data Index: 225857 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.4065. Min Act: -0.0001

Data Index: 946049 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3980. Min Act: -0.0001

Data Index: 1139523 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3884. Min Act: -0.0001

Data Index: 1332170 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3843. Min Act: -0.0001

Data Index: 46703 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3884. Min Act: -0.0001

Data Index: 590034 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3802. Min Act: -0.0001

Data Index: 701007 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3810. Min Act: -0.0001

Data Index: 1352006 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3770. Min Act: -0.0001

Data Index: 18154 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3782. Min Act: -0.0001

Data Index: 1145405 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3762. Min Act: -0.0001

Data Index: 503706 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3767. Min Act: -0.0001

Data Index: 1160952 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3744. Min Act: -0.0001

Data Index: 1141803 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3818. Min Act: -0.0001

Data Index: 967101 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3705. Min Act: -0.0001

Data Index: 1150067 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3779. Min Act: -0.0001

Data Index: 926348 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3698. Min Act: -0.0001

Data Index: 1283361 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3692. Min Act: -0.0001

Data Index: 452842 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3741. Min Act: -0.0002

Data Index: 481484 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3731. Min Act: -0.0001

Data Index: 719461 (C4 (Web Text))

Max Activating Token Index: 168