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

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

Neuron 2731 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: 0.5045. Min Range: -0.5045

Max Act: 0.4691. Min Act: -0.0001

Data Index: 847180 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.5045. Min Act: -0.0001

Data Index: 1327895 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4363. Min Act: -0.0001

Data Index: 487006 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4349. Min Act: -0.0001

Data Index: 1166266 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4113. Min Act: -0.0001

Data Index: 553010 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3864. Min Act: -0.0001

Data Index: 593015 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3818. Min Act: -0.0001

Data Index: 696584 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3939. Min Act: -0.0001

Data Index: 496043 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3921. Min Act: -0.0001

Data Index: 16667 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3899. Min Act: -0.0001

Data Index: 84749 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3575. Min Act: -0.0001

Data Index: 496911 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3757. Min Act: -0.0001

Data Index: 523715 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3815. Min Act: -0.0001

Data Index: 382312 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4708. Min Act: -0.0001

Data Index: 91292 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3540. Min Act: -0.0001

Data Index: 604464 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3345. Min Act: -0.0001

Data Index: 1277601 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3437. Min Act: -0.0001

Data Index: 794143 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.2891. Min Act: -0.0001

Data Index: 205919 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3401. Min Act: -0.0001

Data Index: 214662 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3585. Min Act: -0.0001

Data Index: 1300229 (C4 (Web Text))

Max Activating Token Index: 115