Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 634 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1436. Min Act: -0.0001

Data Index: 219423 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1385. Min Act: -0.0001

Data Index: 415619 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1252. Min Act: -0.0001

Data Index: 1098664 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1308. Min Act: -0.0001

Data Index: 744181 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1216. Min Act: -0.0001

Data Index: 1124481 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1242. Min Act: -0.0001

Data Index: 152643 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1188. Min Act: -0.0001

Data Index: 45813 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1223. Min Act: -0.0001

Data Index: 1244104 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1228. Min Act: -0.0001

Data Index: 766639 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1132. Min Act: -0.0001

Data Index: 770398 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1160. Min Act: -0.0001

Data Index: 797889 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1069. Min Act: -0.0001

Data Index: 1338238 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1117. Min Act: -0.0001

Data Index: 1101868 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1115. Min Act: -0.0001

Data Index: 154809 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1146. Min Act: -0.0001

Data Index: 636608 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1053. Min Act: -0.0001

Data Index: 720287 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1194. Min Act: -0.0001

Data Index: 875263 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1096. Min Act: -0.0001

Data Index: 75383 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1130. Min Act: -0.0001

Data Index: 1229800 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1039. Min Act: -0.0001

Data Index: 436595 (C4 (Web Text))

Max Activating Token Index: 959