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

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

Neuron 1365 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: 0.5975. Min Range: -0.5975

Max Act: 0.5975. Min Act: -0.0002

Data Index: 1320508 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5833. Min Act: -0.0002

Data Index: 1028565 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5893. Min Act: -0.0002

Data Index: 820882 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5798. Min Act: -0.0002

Data Index: 168264 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5787. Min Act: -0.0003

Data Index: 2398 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5538. Min Act: -0.0002

Data Index: 457952 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5587. Min Act: -0.0002

Data Index: 752231 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5622. Min Act: -0.0002

Data Index: 496705 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5641. Min Act: -0.0003

Data Index: 6106 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5428. Min Act: -0.0002

Data Index: 204673 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5461. Min Act: -0.0002

Data Index: 1083242 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5409. Min Act: -0.0003

Data Index: 1245727 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5240. Min Act: -0.0002

Data Index: 535117 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5141. Min Act: -0.0002

Data Index: 474593 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5238. Min Act: -0.0002

Data Index: 26031 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5082. Min Act: -0.0002

Data Index: 590702 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5083. Min Act: -0.0002

Data Index: 404355 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5233. Min Act: -0.0002

Data Index: 1234355 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5051. Min Act: -0.0002

Data Index: 1122244 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.5125. Min Act: -0.0002

Data Index: 914990 (C4 (Web Text))

Max Activating Token Index: 1020