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

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

Neuron 1077 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: 0.1309. Min Range: -0.1309

Max Act: 0.1309. Min Act: -0.0001

Data Index: 1578196 (Python Code)

Max Activating Token Index: 642

Text #1

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1297. Min Act: -0.0001

Data Index: 52947 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1249. Min Act: -0.0001

Data Index: 432258 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1227. Min Act: -0.0001

Data Index: 674690 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1286. Min Act: -0.0001

Data Index: 795489 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1123. Min Act: -0.0001

Data Index: 1189513 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1051. Min Act: -0.0001

Data Index: 1103249 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1237. Min Act: -0.0001

Data Index: 246727 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1103. Min Act: -0.0001

Data Index: 809414 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1066. Min Act: -0.0001

Data Index: 856262 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1105. Min Act: -0.0001

Data Index: 135960 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1035. Min Act: -0.0001

Data Index: 925590 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1076. Min Act: -0.0001

Data Index: 490596 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1039. Min Act: -0.0001

Data Index: 1145437 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1146. Min Act: -0.0001

Data Index: 362059 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1058. Min Act: -0.0001

Data Index: 245256 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1062. Min Act: -0.0001

Data Index: 1125167 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1048. Min Act: -0.0001

Data Index: 173213 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1085. Min Act: -0.0001

Data Index: 805781 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0960. Min Act: -0.0001

Data Index: 370089 (C4 (Web Text))

Max Activating Token Index: 734