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

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

Neuron 615 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0078. Min Act: -0.0003

Data Index: 984037 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0078. Min Act: -0.0003

Data Index: 574737 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0076. Min Act: -0.0003

Data Index: 831719 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0075. Min Act: -0.0003

Data Index: 890884 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0074. Min Act: -0.0003

Data Index: 447030 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0074. Min Act: -0.0003

Data Index: 676198 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0074. Min Act: -0.0003

Data Index: 61078 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0073. Min Act: -0.0003

Data Index: 1321886 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0074. Min Act: -0.0003

Data Index: 40906 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0073. Min Act: -0.0003

Data Index: 770557 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0073. Min Act: -0.0003

Data Index: 608750 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0072. Min Act: -0.0003

Data Index: 721443 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0072. Min Act: -0.0003

Data Index: 457711 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0072. Min Act: -0.0003

Data Index: 41519 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0071. Min Act: -0.0003

Data Index: 1307327 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0072. Min Act: -0.0003

Data Index: 771985 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0071. Min Act: -0.0003

Data Index: 959704 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0071. Min Act: -0.0003

Data Index: 275642 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0070. Min Act: -0.0003

Data Index: 563632 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1135048 (C4 (Web Text))

Max Activating Token Index: 55