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

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

Neuron 45 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: 0.1472. Min Range: -0.1472

Max Act: 0.1472. Min Act: -0.0001

Data Index: 846253 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1276. Min Act: -0.0001

Data Index: 341791 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1305. Min Act: -0.0001

Data Index: 144908 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1277. Min Act: -0.0001

Data Index: 907141 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1206. Min Act: -0.0001

Data Index: 157648 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1239. Min Act: -0.0001

Data Index: 1205142 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1252. Min Act: -0.0001

Data Index: 612427 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1137. Min Act: -0.0001

Data Index: 510189 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1146. Min Act: -0.0001

Data Index: 63936 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1090. Min Act: -0.0001

Data Index: 523147 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1086. Min Act: -0.0001

Data Index: 152561 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1107. Min Act: -0.0001

Data Index: 1146050 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1140. Min Act: -0.0001

Data Index: 1337550 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1083. Min Act: -0.0001

Data Index: 1233412 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1125. Min Act: -0.0001

Data Index: 899417 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1037. Min Act: -0.0001

Data Index: 794222 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1065. Min Act: -0.0001

Data Index: 90701 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1050. Min Act: -0.0001

Data Index: 56497 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1041. Min Act: -0.0001

Data Index: 1065301 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1112427 (C4 (Web Text))

Max Activating Token Index: 983