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

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

Neuron 3193 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: 1.3170. Min Range: -1.3170

Max Act: 1.3170. Min Act: -0.0001

Data Index: 909335 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.1256. Min Act: -0.0001

Data Index: 1107940 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.1149. Min Act: -0.0001

Data Index: 515728 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.0822. Min Act: -0.0001

Data Index: 461439 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.0708. Min Act: -0.0001

Data Index: 829291 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.9982. Min Act: -0.0000

Data Index: 724253 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.0468. Min Act: -0.0000

Data Index: 578215 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.0501. Min Act: -0.0001

Data Index: 658852 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.0186. Min Act: -0.0001

Data Index: 1190565 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.0122. Min Act: -0.0001

Data Index: 612519 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.0434. Min Act: -0.0001

Data Index: 1357623 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.9863. Min Act: -0.0001

Data Index: 894964 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.9512. Min Act: -0.0001

Data Index: 1301226 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.9970. Min Act: -0.0001

Data Index: 15760 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.9937. Min Act: -0.0001

Data Index: 815662 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.9641. Min Act: -0.0001

Data Index: 834455 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.9606. Min Act: -0.0001

Data Index: 317536 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.9759. Min Act: -0.0001

Data Index: 998538 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.9372. Min Act: -0.0001

Data Index: 1230095 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1252564 (C4 (Web Text))

Max Activating Token Index: 468