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

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

Neuron 1415 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: 1.4798. Min Range: -1.4798

Max Act: 1.4798. Min Act: -0.0002

Data Index: 87721 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.4620. Min Act: -0.0002

Data Index: 1041389 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.4431. Min Act: -0.0002

Data Index: 153808 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.4202. Min Act: -0.0002

Data Index: 255978 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.3693. Min Act: -0.0002

Data Index: 1151532 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.3016. Min Act: -0.0002

Data Index: 990020 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.2801. Min Act: -0.0002

Data Index: 244114 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.3109. Min Act: -0.0002

Data Index: 582549 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.2998. Min Act: -0.0002

Data Index: 1215640 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.3240. Min Act: -0.0002

Data Index: 484577 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.3195. Min Act: -0.0002

Data Index: 524766 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.2952. Min Act: -0.0002

Data Index: 559064 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.2691. Min Act: -0.0002

Data Index: 145720 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.2603. Min Act: -0.0002

Data Index: 404177 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.2897. Min Act: -0.0002

Data Index: 161539 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.2654. Min Act: -0.0002

Data Index: 364548 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.3014. Min Act: -0.0002

Data Index: 930537 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.2757. Min Act: -0.0002

Data Index: 986255 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.2441. Min Act: -0.0002

Data Index: 680855 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 1.4798. Min Range: -1.4798

Max Act: 1.2671. Min Act: -0.0002

Data Index: 478245 (C4 (Web Text))

Max Activating Token Index: 613