Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 431 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1362. Min Act: -0.0002

Data Index: 379571 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1400. Min Act: -0.0002

Data Index: 1081679 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1370. Min Act: -0.0002

Data Index: 32848 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1195. Min Act: -0.0002

Data Index: 898449 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1168. Min Act: -0.0002

Data Index: 1200331 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1156. Min Act: -0.0002

Data Index: 1281435 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1152. Min Act: -0.0002

Data Index: 197010 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1142. Min Act: -0.0002

Data Index: 1228820 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1138. Min Act: -0.0002

Data Index: 346460 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1155. Min Act: -0.0002

Data Index: 1250058 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1150. Min Act: -0.0002

Data Index: 1357909 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1112. Min Act: -0.0002

Data Index: 547564 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1086. Min Act: -0.0002

Data Index: 95218 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1103. Min Act: -0.0002

Data Index: 702112 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1099. Min Act: -0.0002

Data Index: 1271621 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1102. Min Act: -0.0002

Data Index: 871975 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1128. Min Act: -0.0002

Data Index: 477757 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1078. Min Act: -0.0002

Data Index: 154375 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1106. Min Act: -0.0002

Data Index: 785310 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1101. Min Act: -0.0002

Data Index: 591750 (C4 (Web Text))

Max Activating Token Index: 295