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

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

Neuron 3672 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0175. Min Range: -1.0175

Max Act: 1.0175. Min Act: -0.0000

Data Index: 54258 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 1.0175. Min Range: -1.0175

Max Act: 1.0156. Min Act: -0.0000

Data Index: 327624 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.9357. Min Act: -0.0000

Data Index: 527025 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.8686. Min Act: 0.0000

Data Index: 284891 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.8659. Min Act: 0.0000

Data Index: 1215662 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.9598. Min Act: 0.0000

Data Index: 1212325 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.8602. Min Act: 0.0000

Data Index: 1306809 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.9026. Min Act: -0.0000

Data Index: 37569 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.8456. Min Act: -0.0000

Data Index: 257291 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.8093. Min Act: 0.0000

Data Index: 397771 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.8091. Min Act: 0.0000

Data Index: 1004802 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.8205. Min Act: -0.0000

Data Index: 937260 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.8167. Min Act: -0.0000

Data Index: 1215027 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.7990. Min Act: -0.0000

Data Index: 771723 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.8487. Min Act: -0.0000

Data Index: 963325 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.8728. Min Act: -0.0000

Data Index: 210104 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1333353 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.8147. Min Act: 0.0000

Data Index: 914033 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.7996. Min Act: -0.0000

Data Index: 697468 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 1.0175. Min Range: -1.0175

Max Act: 0.7631. Min Act: -0.0000

Data Index: 933485 (C4 (Web Text))

Max Activating Token Index: 323