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

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

Neuron 4684 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.5810. Min Act: -0.0000

Data Index: 45193 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.4607. Min Act: -0.0000

Data Index: 907777 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.4200. Min Act: -0.0000

Data Index: 419842 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.5039. Min Act: -0.0000

Data Index: 989380 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.4628. Min Act: -0.0000

Data Index: 170994 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.4492. Min Act: -0.0000

Data Index: 695780 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.4369. Min Act: -0.0000

Data Index: 117353 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.4362. Min Act: -0.0000

Data Index: 664010 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.2929. Min Act: -0.0000

Data Index: 1343143 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.3555. Min Act: -0.0000

Data Index: 811746 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.3302. Min Act: -0.0000

Data Index: 852798 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.3165. Min Act: -0.0000

Data Index: 807734 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.3101. Min Act: -0.0000

Data Index: 430102 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.1699. Min Act: -0.0000

Data Index: 975699 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.2957. Min Act: -0.0000

Data Index: 810692 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.2834. Min Act: -0.0000

Data Index: 719001 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.2891. Min Act: -0.0000

Data Index: 858243 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.2675. Min Act: -0.0000

Data Index: 302190 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.3435. Min Act: -0.0000

Data Index: 48110 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 1.5810. Min Range: -1.5810

Max Act: 1.1908. Min Act: -0.0000

Data Index: 319028 (C4 (Web Text))

Max Activating Token Index: 346