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

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

Neuron 14 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: 3.2908. Min Range: -3.2908

Max Act: 3.2908. Min Act: -0.1700

Data Index: 1100448 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 3.2908. Min Range: -3.2908

Max Act: 3.2861. Min Act: -0.1700

Data Index: 221591 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 3.2908. Min Range: -3.2908

Max Act: 3.2643. Min Act: -0.1700

Data Index: 685104 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 3.2908. Min Range: -3.2908

Max Act: 3.2155. Min Act: -0.1700

Data Index: 1327492 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 3.2908. Min Range: -3.2908

Max Act: 3.2052. Min Act: -0.1700

Data Index: 378497 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 3.2908. Min Range: -3.2908

Max Act: 3.2126. Min Act: -0.1700

Data Index: 1073341 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 3.2908. Min Range: -3.2908

Max Act: 3.1721. Min Act: -0.1700

Data Index: 991563 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 3.2908. Min Range: -3.2908

Max Act: 3.1661. Min Act: -0.1700

Data Index: 103802 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 3.2908. Min Range: -3.2908

Max Act: 3.1680. Min Act: -0.1700

Data Index: 780843 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 3.2908. Min Range: -3.2908

Max Act: 3.1669. Min Act: -0.1700

Data Index: 391135 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 3.2908. Min Range: -3.2908

Max Act: 3.1453. Min Act: -0.1700

Data Index: 496896 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 3.2908. Min Range: -3.2908

Max Act: 3.1575. Min Act: -0.1700

Data Index: 540780 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 3.2908. Min Range: -3.2908

Max Act: 3.1418. Min Act: -0.1700

Data Index: 868795 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 3.2908. Min Range: -3.2908

Max Act: 3.1459. Min Act: -0.1700

Data Index: 979120 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 3.2908. Min Range: -3.2908

Max Act: 3.1299. Min Act: -0.1700

Data Index: 367470 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 3.2908. Min Range: -3.2908

Max Act: 3.1239. Min Act: -0.1700

Data Index: 1339309 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 3.2908. Min Range: -3.2908

Max Act: 3.1259. Min Act: -0.1700

Data Index: 305490 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 3.2908. Min Range: -3.2908

Max Act: 3.1068. Min Act: -0.1700

Data Index: 1172987 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 3.2908. Min Range: -3.2908

Max Act: 3.1146. Min Act: -0.1700

Data Index: 98158 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 3.2908. Min Range: -3.2908

Max Act: 3.0953. Min Act: -0.1700

Data Index: 642596 (C4 (Web Text))

Max Activating Token Index: 412