Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2766 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.9888. Min Act: -0.0000

Data Index: 112884 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.9082. Min Act: -0.0000

Data Index: 1110090 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.8012. Min Act: -0.0000

Data Index: 661903 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.8344. Min Act: -0.0000

Data Index: 179995 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.8250. Min Act: -0.0000

Data Index: 114844 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.8098. Min Act: -0.0000

Data Index: 426436 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.6882. Min Act: -0.0000

Data Index: 132829 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.6970. Min Act: -0.0000

Data Index: 473726 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.6751. Min Act: -0.0000

Data Index: 680797 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1262468 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.6256. Min Act: -0.0000

Data Index: 444074 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.5947. Min Act: -0.0000

Data Index: 912495 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.6062. Min Act: -0.0000

Data Index: 892568 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.5832. Min Act: -0.0000

Data Index: 610925 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.6196. Min Act: -0.0000

Data Index: 78131 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.5945. Min Act: -0.0000

Data Index: 500565 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.5662. Min Act: -0.0000

Data Index: 209372 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.5759. Min Act: -0.0000

Data Index: 1329429 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.6157. Min Act: -0.0000

Data Index: 768857 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.9888. Min Range: -0.9888

Max Act: 0.6050. Min Act: -0.0000

Data Index: 782890 (C4 (Web Text))

Max Activating Token Index: 226