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

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

Neuron 1259 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.7712. Min Act: -0.0001

Data Index: 74775 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.7899. Min Act: -0.0001

Data Index: 130320 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.7905. Min Act: -0.0001

Data Index: 856601 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.7033. Min Act: -0.0001

Data Index: 1285535 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.7198. Min Act: -0.0001

Data Index: 1199350 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.7367. Min Act: -0.0001

Data Index: 849031 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.7009. Min Act: -0.0001

Data Index: 525498 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.7286. Min Act: -0.0001

Data Index: 263382 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.6793. Min Act: -0.0001

Data Index: 710008 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.7015. Min Act: -0.0001

Data Index: 579227 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.6656. Min Act: -0.0001

Data Index: 1041319 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.6857. Min Act: -0.0001

Data Index: 982975 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.6114. Min Act: -0.0001

Data Index: 365429 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.6545. Min Act: -0.0001

Data Index: 139039 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.6472. Min Act: -0.0001

Data Index: 1172488 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.6088. Min Act: -0.0001

Data Index: 1261225 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.6870. Min Act: -0.0001

Data Index: 63240 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.6588. Min Act: -0.0001

Data Index: 3407 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.6954. Min Act: -0.0001

Data Index: 733802 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.7905. Min Range: -0.7905

Max Act: 0.6470. Min Act: -0.0001

Data Index: 286921 (C4 (Web Text))

Max Activating Token Index: 210