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

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

Neuron 5571 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: 0.7562. Min Range: -0.7562

Max Act: 0.7562. Min Act: -0.0002

Data Index: 572587 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6938. Min Act: -0.0002

Data Index: 1021736 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6830. Min Act: -0.0002

Data Index: 243405 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6898. Min Act: -0.0002

Data Index: 1149228 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6896. Min Act: -0.0002

Data Index: 368247 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6871. Min Act: -0.0002

Data Index: 1286000 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6765. Min Act: -0.0002

Data Index: 251826 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6750. Min Act: -0.0002

Data Index: 643587 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6788. Min Act: -0.0002

Data Index: 357598 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6531. Min Act: -0.0002

Data Index: 625718 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6499. Min Act: -0.0002

Data Index: 1043436 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6539. Min Act: -0.0002

Data Index: 1187783 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6435. Min Act: -0.0002

Data Index: 310960 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6343. Min Act: -0.0002

Data Index: 1071138 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6503. Min Act: -0.0002

Data Index: 953520 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6310. Min Act: -0.0002

Data Index: 1306397 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6363. Min Act: -0.0002

Data Index: 856934 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6370. Min Act: -0.0002

Data Index: 369825 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6281. Min Act: -0.0002

Data Index: 777797 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6316. Min Act: -0.0002

Data Index: 947353 (C4 (Web Text))

Max Activating Token Index: 36