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

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

Neuron 3535 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.8489. Min Act: -0.0000

Data Index: 783213 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.7183. Min Act: -0.0000

Data Index: 294566 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.7139. Min Act: -0.0000

Data Index: 176446 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.6654. Min Act: -0.0000

Data Index: 876663 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1039104 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5930. Min Act: -0.0000

Data Index: 101437 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1092992 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5899. Min Act: -0.0000

Data Index: 910344 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1282954 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5147. Min Act: -0.0000

Data Index: 213689 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5390. Min Act: -0.0000

Data Index: 871778 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1067380 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1109400 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5071. Min Act: -0.0000

Data Index: 814552 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.4923. Min Act: -0.0000

Data Index: 1124515 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5059. Min Act: -0.0000

Data Index: 216259 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.5109. Min Act: -0.0000

Data Index: 880376 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.4849. Min Act: -0.0000

Data Index: 270486 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.4828. Min Act: -0.0000

Data Index: 823777 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.8489. Min Range: -0.8489

Max Act: 0.4996. Min Act: 0.0000

Data Index: 679992 (C4 (Web Text))

Max Activating Token Index: 689