Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3644 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.7163. Min Act: -0.0001

Data Index: 560517 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.6517. Min Act: -0.0001

Data Index: 159990 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.6534. Min Act: -0.0001

Data Index: 1216649 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5800. Min Act: -0.0001

Data Index: 1276335 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.6038. Min Act: -0.0001

Data Index: 576748 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5663. Min Act: -0.0001

Data Index: 298051 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5341. Min Act: -0.0001

Data Index: 280002 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5171. Min Act: -0.0001

Data Index: 1015737 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5346. Min Act: -0.0001

Data Index: 470533 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5729. Min Act: -0.0001

Data Index: 511281 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5347. Min Act: -0.0001

Data Index: 692231 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5438. Min Act: -0.0001

Data Index: 978686 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5657. Min Act: -0.0001

Data Index: 19878 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5580. Min Act: -0.0001

Data Index: 469401 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5692. Min Act: -0.0001

Data Index: 390055 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.4884. Min Act: -0.0001

Data Index: 30751 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5302. Min Act: -0.0001

Data Index: 70344 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5256. Min Act: -0.0001

Data Index: 457537 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.4901. Min Act: -0.0001

Data Index: 315262 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5544. Min Act: -0.0001

Data Index: 1283208 (C4 (Web Text))

Max Activating Token Index: 1017