Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 500 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3582. Min Act: -0.0001

Data Index: 316402 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3620. Min Act: -0.0001

Data Index: 176656 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3445. Min Act: -0.0001

Data Index: 982555 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3346. Min Act: -0.0001

Data Index: 836645 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3332. Min Act: -0.0001

Data Index: 392573 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3328. Min Act: -0.0001

Data Index: 1218271 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3179. Min Act: -0.0001

Data Index: 510737 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3065. Min Act: -0.0001

Data Index: 670916 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3041. Min Act: -0.0001

Data Index: 94681 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3114. Min Act: -0.0001

Data Index: 306881 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3091. Min Act: -0.0000

Data Index: 854616 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2869. Min Act: -0.0001

Data Index: 52776 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2821. Min Act: -0.0001

Data Index: 347598 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3099. Min Act: -0.0001

Data Index: 431177 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3202. Min Act: -0.0001

Data Index: 784422 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3302. Min Act: -0.0001

Data Index: 1061496 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3028. Min Act: -0.0000

Data Index: 1289163 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3032. Min Act: -0.0001

Data Index: 295255 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2802. Min Act: -0.0001

Data Index: 477347 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3067. Min Act: -0.0001

Data Index: 734347 (C4 (Web Text))

Max Activating Token Index: 172