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

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

Neuron 1847 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.8846. Min Act: -0.0001

Data Index: 1164836 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.6304. Min Act: -0.0001

Data Index: 705537 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.4060. Min Act: -0.0001

Data Index: 775924 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.3283. Min Act: -0.0001

Data Index: 167061 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.4379. Min Act: -0.0001

Data Index: 1279935 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.5413. Min Act: -0.0001

Data Index: 85485 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.5338. Min Act: -0.0001

Data Index: 1345194 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.2552. Min Act: -0.0001

Data Index: 133261 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.4205. Min Act: -0.0001

Data Index: 156418 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.3289. Min Act: -0.0001

Data Index: 1242554 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.3447. Min Act: -0.0001

Data Index: 1138847 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.3086. Min Act: -0.0001

Data Index: 522127 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.2202. Min Act: -0.0001

Data Index: 738003 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.3247. Min Act: -0.0001

Data Index: 55813 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.2439. Min Act: -0.0001

Data Index: 415208 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.1802. Min Act: -0.0001

Data Index: 1302446 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.2238. Min Act: -0.0001

Data Index: 1182468 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.1301. Min Act: -0.0001

Data Index: 886841 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.1976. Min Act: -0.0001

Data Index: 275090 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 1.8846. Min Range: -1.8846

Max Act: 1.2053. Min Act: -0.0001

Data Index: 791828 (C4 (Web Text))

Max Activating Token Index: 314