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

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

Neuron 786 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.7659. Min Act: -0.0000

Data Index: 349525 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.6247. Min Act: -0.0000

Data Index: 145842 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.6701. Min Act: -0.0000

Data Index: 581107 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.5935. Min Act: -0.0000

Data Index: 612572 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.6242. Min Act: -0.0000

Data Index: 769974 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.5821. Min Act: -0.0000

Data Index: 659657 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.5079. Min Act: -0.0000

Data Index: 50999 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.5524. Min Act: -0.0000

Data Index: 496551 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.5656. Min Act: -0.0000

Data Index: 152206 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.5066. Min Act: -0.0000

Data Index: 387875 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.5232. Min Act: -0.0000

Data Index: 114408 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.5380. Min Act: -0.0000

Data Index: 1059166 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.5494. Min Act: -0.0000

Data Index: 340148 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.5020. Min Act: -0.0000

Data Index: 376922 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.5266. Min Act: -0.0000

Data Index: 274342 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.5600. Min Act: -0.0000

Data Index: 397901 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.4912. Min Act: -0.0000

Data Index: 384331 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1164348 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1023670 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.7659. Min Range: -0.7659

Max Act: 0.5022. Min Act: -0.0000

Data Index: 821482 (C4 (Web Text))

Max Activating Token Index: 814