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

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

Neuron 3890 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0025. Min Range: -2.0025

Max Act: 2.0025. Min Act: -0.0000

Data Index: 824410 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.9185. Min Act: -0.0001

Data Index: 1281164 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.6219. Min Act: -0.0000

Data Index: 947350 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.6303. Min Act: -0.0001

Data Index: 1275195 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.4800. Min Act: -0.0001

Data Index: 1256297 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.5428. Min Act: -0.0000

Data Index: 2722 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.3993. Min Act: -0.0001

Data Index: 1181501 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.5046. Min Act: -0.0000

Data Index: 776137 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.3456. Min Act: -0.0001

Data Index: 254475 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.4204. Min Act: -0.0001

Data Index: 1167822 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.3233. Min Act: -0.0000

Data Index: 680041 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.3019. Min Act: -0.0000

Data Index: 810385 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.2742. Min Act: -0.0000

Data Index: 989711 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.2234. Min Act: -0.0001

Data Index: 210920 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.1861. Min Act: -0.0000

Data Index: 951333 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.2429. Min Act: -0.0000

Data Index: 1166897 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.1819. Min Act: -0.0001

Data Index: 138381 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.1065. Min Act: -0.0001

Data Index: 959476 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.2132. Min Act: -0.0001

Data Index: 1349890 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 2.0025. Min Range: -2.0025

Max Act: 1.2105. Min Act: -0.0001

Data Index: 305555 (C4 (Web Text))

Max Activating Token Index: 978