Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1025 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.5952. Min Act: -0.1700

Data Index: 98263 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.3922. Min Act: -0.1672

Data Index: 1215662 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.2805. Min Act: -0.1661

Data Index: 794223 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.2745. Min Act: -0.1700

Data Index: 692861 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.2384. Min Act: -0.1417

Data Index: 44347 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.2124. Min Act: -0.1700

Data Index: 673188 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.2093. Min Act: -0.1700

Data Index: 916078 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.1914. Min Act: -0.1584

Data Index: 1037610 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.1962. Min Act: -0.1700

Data Index: 938642 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.1600. Min Act: -0.1700

Data Index: 439740 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.1544. Min Act: -0.1693

Data Index: 1043160 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.1544. Min Act: -0.1700

Data Index: 871054 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.1475. Min Act: -0.1700

Data Index: 910118 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.1525. Min Act: -0.1700

Data Index: 1058033 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.1241. Min Act: -0.1699

Data Index: 2113 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.1231. Min Act: -0.1653

Data Index: 708623 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.1096. Min Act: -0.1699

Data Index: 602708 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.1173. Min Act: -0.1700

Data Index: 347903 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.1057. Min Act: -0.1700

Data Index: 1160540 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 3.5952. Min Range: -3.5952

Max Act: 3.0914. Min Act: -0.1700

Data Index: 1134796 (C4 (Web Text))

Max Activating Token Index: 822