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

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

Neuron 4434 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3880. Min Range: -2.3880

Max Act: 2.3880. Min Act: -0.0000

Data Index: 582949 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 2.3880. Min Range: -2.3880

Max Act: 2.1883. Min Act: -0.0000

Data Index: 1107649 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 2.3880. Min Range: -2.3880

Max Act: 2.2120. Min Act: -0.0000

Data Index: 495124 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 2.3880. Min Range: -2.3880

Max Act: 1.7558. Min Act: -0.0000

Data Index: 1020879 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 2.3880. Min Range: -2.3880

Max Act: 1.9204. Min Act: -0.0000

Data Index: 45115 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 2.3880. Min Range: -2.3880

Max Act: 1.8889. Min Act: -0.0000

Data Index: 728788 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 2.3880. Min Range: -2.3880

Max Act: 1.8589. Min Act: -0.0000

Data Index: 108288 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 2.3880. Min Range: -2.3880

Max Act: 1.8484. Min Act: -0.0000

Data Index: 68921 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 2.3880. Min Range: -2.3880

Max Act: 1.9489. Min Act: -0.0000

Data Index: 738482 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 2.3880. Min Range: -2.3880

Max Act: 1.6503. Min Act: -0.0000

Data Index: 82684 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 2.3880. Min Range: -2.3880

Max Act: 1.8716. Min Act: -0.0000

Data Index: 1052263 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 2.3880. Min Range: -2.3880

Max Act: 1.7459. Min Act: -0.0000

Data Index: 275264 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 2.3880. Min Range: -2.3880

Max Act: 1.8407. Min Act: -0.0000

Data Index: 543667 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 2.3880. Min Range: -2.3880

Max Act: 1.5477. Min Act: -0.0000

Data Index: 55446 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 2.3880. Min Range: -2.3880

Max Act: 2.0294. Min Act: -0.0000

Data Index: 370625 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 2.3880. Min Range: -2.3880

Max Act: 1.7164. Min Act: -0.0000

Data Index: 126279 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 2.3880. Min Range: -2.3880

Max Act: 1.7172. Min Act: -0.0000

Data Index: 1197511 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 2.3880. Min Range: -2.3880

Max Act: 1.7956. Min Act: -0.0000

Data Index: 720516 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 2.3880. Min Range: -2.3880

Max Act: 1.7796. Min Act: -0.0000

Data Index: 663309 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 2.3880. Min Range: -2.3880

Max Act: 1.8862. Min Act: -0.0000

Data Index: 990914 (C4 (Web Text))

Max Activating Token Index: 197