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

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

Neuron 2733 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: 0.1471. Min Range: -0.1471

Max Act: 0.1471. Min Act: -0.0001

Data Index: 1000019 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1180. Min Act: -0.0001

Data Index: 48148 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1246. Min Act: -0.0001

Data Index: 464306 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1254. Min Act: 0.0004

Data Index: 442475 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1223157 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1161. Min Act: -0.0001

Data Index: 1172237 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1153. Min Act: -0.0001

Data Index: 161038 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1193. Min Act: -0.0001

Data Index: 227427 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1104. Min Act: -0.0001

Data Index: 1272516 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1149. Min Act: -0.0001

Data Index: 531884 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1174. Min Act: -0.0001

Data Index: 1290827 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1094. Min Act: -0.0001

Data Index: 511254 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1226244 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1118. Min Act: -0.0001

Data Index: 1327902 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1091. Min Act: -0.0001

Data Index: 1109538 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1337646 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1102. Min Act: -0.0001

Data Index: 1284245 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1082558 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1100. Min Act: -0.0001

Data Index: 807451 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1306844 (C4 (Web Text))

Max Activating Token Index: 115