Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5503 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7036. Min Range: -4.7036

Max Act: 4.7036. Min Act: -0.0000

Data Index: 866834 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 4.7036. Min Range: -4.7036

Max Act: 3.7806. Min Act: -0.0000

Data Index: 528401 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 4.7036. Min Range: -4.7036

Max Act: 3.8373. Min Act: -0.0000

Data Index: 499172 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 4.7036. Min Range: -4.7036

Max Act: 3.5235. Min Act: -0.0000

Data Index: 499013 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 4.7036. Min Range: -4.7036

Max Act: 3.1422. Min Act: -0.0000

Data Index: 853153 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 4.7036. Min Range: -4.7036

Max Act: 3.2628. Min Act: -0.0000

Data Index: 951278 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 4.7036. Min Range: -4.7036

Max Act: 3.1929. Min Act: -0.0000

Data Index: 1193055 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 4.7036. Min Range: -4.7036

Max Act: 2.9523. Min Act: -0.0000

Data Index: 1025042 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 4.7036. Min Range: -4.7036

Max Act: 3.0579. Min Act: -0.0000

Data Index: 518956 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 4.7036. Min Range: -4.7036

Max Act: 2.9816. Min Act: -0.0000

Data Index: 600645 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 4.7036. Min Range: -4.7036

Max Act: 3.2709. Min Act: -0.0000

Data Index: 759619 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 4.7036. Min Range: -4.7036

Max Act: 2.9806. Min Act: -0.0000

Data Index: 273105 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 4.7036. Min Range: -4.7036

Max Act: 3.0297. Min Act: -0.0000

Data Index: 629247 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 4.7036. Min Range: -4.7036

Max Act: 2.7318. Min Act: -0.0000

Data Index: 1120712 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 4.7036. Min Range: -4.7036

Max Act: 3.0031. Min Act: -0.0000

Data Index: 1146271 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 4.7036. Min Range: -4.7036

Max Act: 2.9900. Min Act: -0.0000

Data Index: 824624 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 4.7036. Min Range: -4.7036

Max Act: 2.6829. Min Act: -0.0000

Data Index: 132353 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 4.7036. Min Range: -4.7036

Max Act: 2.9559. Min Act: -0.0000

Data Index: 63990 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 4.7036. Min Range: -4.7036

Max Act: 2.7751. Min Act: -0.0000

Data Index: 17633 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 4.7036. Min Range: -4.7036

Max Act: 3.0321. Min Act: -0.0000

Data Index: 112232 (C4 (Web Text))

Max Activating Token Index: 765