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

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

Neuron 2669 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7071. Min Range: -2.7071

Max Act: 2.7071. Min Act: 0.0000

Data Index: 971767 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 2.7071. Min Range: -2.7071

Max Act: 2.6395. Min Act: -0.0000

Data Index: 778590 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 2.7071. Min Range: -2.7071

Max Act: 2.4070. Min Act: -0.0000

Data Index: 799327 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 2.7071. Min Range: -2.7071

Max Act: 2.3614. Min Act: 0.0001

Data Index: 214301 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 2.7071. Min Range: -2.7071

Max Act: 2.4383. Min Act: 0.0000

Data Index: 394721 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 2.7071. Min Range: -2.7071

Max Act: 2.2421. Min Act: -0.0000

Data Index: 995171 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 2.7071. Min Range: -2.7071

Max Act: 2.3295. Min Act: -0.0000

Data Index: 1356068 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 2.7071. Min Range: -2.7071

Max Act: 2.2781. Min Act: -0.0000

Data Index: 466352 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 2.7071. Min Range: -2.7071

Max Act: 2.3962. Min Act: 0.0000

Data Index: 789265 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 2.7071. Min Range: -2.7071

Max Act: 2.1537. Min Act: 0.0001

Data Index: 1159167 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 2.7071. Min Range: -2.7071

Max Act: 2.2500. Min Act: 0.0000

Data Index: 1001099 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 2.7071. Min Range: -2.7071

Max Act: 2.1270. Min Act: -0.0000

Data Index: 76541 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 2.7071. Min Range: -2.7071

Max Act: 2.1178. Min Act: -0.0000

Data Index: 132886 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 2.7071. Min Range: -2.7071

Max Act: 2.1946. Min Act: -0.0000

Data Index: 348013 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 2.7071. Min Range: -2.7071

Max Act: 2.2905. Min Act: -0.0000

Data Index: 1007580 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 2.7071. Min Range: -2.7071

Max Act: 2.0424. Min Act: -0.0000

Data Index: 1042267 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 2.7071. Min Range: -2.7071

Max Act: 2.0257. Min Act: 0.0001

Data Index: 767061 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 2.7071. Min Range: -2.7071

Max Act: 2.0421. Min Act: -0.0000

Data Index: 307238 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 2.7071. Min Range: -2.7071

Max Act: 2.0119. Min Act: -0.0000

Data Index: 317824 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 2.7071. Min Range: -2.7071

Max Act: 1.9690. Min Act: -0.0000

Data Index: 408661 (C4 (Web Text))

Max Activating Token Index: 623