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

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

Neuron 1540 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: 4.3060. Min Range: -4.3060

Max Act: 4.3060. Min Act: -0.1699

Data Index: 1606092 (Python Code)

Max Activating Token Index: 227

Text #1

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2379. Min Act: -0.1700

Data Index: 972601 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2010. Min Act: -0.1678

Data Index: 1428120 (Python Code)

Max Activating Token Index: 975

Text #3

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.1837. Min Act: -0.1678

Data Index: 164069 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.1210. Min Act: -0.1678

Data Index: 1478761 (Python Code)

Max Activating Token Index: 203

Text #5

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.1361. Min Act: -0.1700

Data Index: 171429 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.1017. Min Act: -0.1699

Data Index: 1635760 (Python Code)

Max Activating Token Index: 575

Text #7

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.1024. Min Act: -0.1684

Data Index: 1501798 (Python Code)

Max Activating Token Index: 491

Text #8

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.1051. Min Act: -0.1678

Data Index: 1465277 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.1089. Min Act: -0.1699

Data Index: 1395856 (Python Code)

Max Activating Token Index: 1005

Text #10

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.1193. Min Act: -0.1700

Data Index: 1309264 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.0552. Min Act: -0.1700

Data Index: 1195586 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.0811. Min Act: -0.1678

Data Index: 1384481 (Python Code)

Max Activating Token Index: 464

Text #13

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.0884. Min Act: -0.1697

Data Index: 1447750 (Python Code)

Max Activating Token Index: 763

Text #14

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.0733. Min Act: -0.1678

Data Index: 1486045 (Python Code)

Max Activating Token Index: 662

Text #15

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.0806. Min Act: -0.1697

Data Index: 1337792 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.0319. Min Act: -0.1698

Data Index: 1542159 (Python Code)

Max Activating Token Index: 946

Text #17

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.0462. Min Act: -0.1699

Data Index: 1360040 (Python Code)

Max Activating Token Index: 359

Text #18

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.0249. Min Act: -0.1700

Data Index: 1431881 (Python Code)

Max Activating Token Index: 785

Text #19

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.0261. Min Act: -0.1699

Data Index: 352042 (C4 (Web Text))

Max Activating Token Index: 371