Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 146 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.2452. Min Range: -7.2452

Max Act: 7.2452. Min Act: -0.1700

Data Index: 1366861 (Python Code)

Max Activating Token Index: 684

Text #1

Max Range: 7.2452. Min Range: -7.2452

Max Act: 7.1827. Min Act: -0.1700

Data Index: 1405577 (Python Code)

Max Activating Token Index: 906

Text #2

Max Range: 7.2452. Min Range: -7.2452

Max Act: 7.1202. Min Act: -0.1700

Data Index: 1549191 (Python Code)

Max Activating Token Index: 832

Text #3

Max Range: 7.2452. Min Range: -7.2452

Max Act: 7.1202. Min Act: -0.1700

Data Index: 1501877 (Python Code)

Max Activating Token Index: 369

Text #4

Max Range: 7.2452. Min Range: -7.2452

Max Act: 7.0889. Min Act: -0.1700

Data Index: 1431005 (Python Code)

Max Activating Token Index: 810

Text #5

Max Range: 7.2452. Min Range: -7.2452

Max Act: 7.0577. Min Act: -0.1700

Data Index: 1374812 (Python Code)

Max Activating Token Index: 882

Text #6

Max Range: 7.2452. Min Range: -7.2452

Max Act: 7.0577. Min Act: -0.1700

Data Index: 1389935 (Python Code)

Max Activating Token Index: 1002

Text #7

Max Range: 7.2452. Min Range: -7.2452

Max Act: 6.9952. Min Act: -0.1700

Data Index: 1511349 (Python Code)

Max Activating Token Index: 991

Text #8

Max Range: 7.2452. Min Range: -7.2452

Max Act: 6.9952. Min Act: -0.1700

Data Index: 1452271 (Python Code)

Max Activating Token Index: 818

Text #9

Max Range: 7.2452. Min Range: -7.2452

Max Act: 6.9952. Min Act: -0.1700

Data Index: 1414149 (Python Code)

Max Activating Token Index: 974

Text #10

Max Range: 7.2452. Min Range: -7.2452

Max Act: 7.0577. Min Act: -0.1700

Data Index: 1386355 (Python Code)

Max Activating Token Index: 921

Text #11

Max Range: 7.2452. Min Range: -7.2452

Max Act: 6.9952. Min Act: -0.1700

Data Index: 1363633 (Python Code)

Max Activating Token Index: 998

Text #12

Max Range: 7.2452. Min Range: -7.2452

Max Act: 6.9639. Min Act: -0.1700

Data Index: 1553043 (Python Code)

Max Activating Token Index: 684

Text #13

Max Range: 7.2452. Min Range: -7.2452

Max Act: 6.9327. Min Act: -0.1700

Data Index: 1437919 (Python Code)

Max Activating Token Index: 684

Text #14

Max Range: 7.2452. Min Range: -7.2452

Max Act: 6.9639. Min Act: -0.1700

Data Index: 1491036 (Python Code)

Max Activating Token Index: 654

Text #15

Max Range: 7.2452. Min Range: -7.2452

Max Act: 6.9327. Min Act: -0.1700

Data Index: 1574849 (Python Code)

Max Activating Token Index: 845

Text #16

Max Range: 7.2452. Min Range: -7.2452

Max Act: 6.8702. Min Act: -0.1700

Data Index: 1398488 (Python Code)

Max Activating Token Index: 886

Text #17

Max Range: 7.2452. Min Range: -7.2452

Max Act: 6.9327. Min Act: -0.1700

Data Index: 1523519 (Python Code)

Max Activating Token Index: 976

Text #18

Max Range: 7.2452. Min Range: -7.2452

Max Act: 6.9327. Min Act: -0.1700

Data Index: 1543358 (Python Code)

Max Activating Token Index: 1014

Text #19

Max Range: 7.2452. Min Range: -7.2452

Max Act: 6.9327. Min Act: -0.1700

Data Index: 1512676 (Python Code)

Max Activating Token Index: 442