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

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

Neuron 3420 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.6728. Min Act: -0.0001

Data Index: 953172 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.5585. Min Act: -0.0001

Data Index: 644474 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.5258. Min Act: -0.0002

Data Index: 781265 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.4895. Min Act: -0.0002

Data Index: 160737 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.4313. Min Act: -0.0001

Data Index: 780428 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.3229. Min Act: -0.0002

Data Index: 802617 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.3513. Min Act: -0.0001

Data Index: 303390 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.3484. Min Act: -0.0002

Data Index: 1090163 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.3414. Min Act: -0.0001

Data Index: 959927 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.2703. Min Act: -0.0001

Data Index: 1246558 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.3359. Min Act: -0.0001

Data Index: 621753 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.3570. Min Act: -0.0001

Data Index: 1133683 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.3064. Min Act: -0.0001

Data Index: 666891 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.3747. Min Act: -0.0001

Data Index: 54562 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.2132. Min Act: -0.0001

Data Index: 1219034 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.2851. Min Act: -0.0001

Data Index: 640676 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.2903. Min Act: -0.0001

Data Index: 541019 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.3139. Min Act: -0.0002

Data Index: 265063 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.2784. Min Act: -0.0001

Data Index: 552663 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 1.6728. Min Range: -1.6728

Max Act: 1.2731. Min Act: -0.0001

Data Index: 710321 (C4 (Web Text))

Max Activating Token Index: 1002