Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1082 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.2346. Min Act: -0.1700

Data Index: 1577230 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.2189. Min Act: -0.1700

Data Index: 1388529 (Python Code)

Max Activating Token Index: 72

Text #2

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.2189. Min Act: -0.1700

Data Index: 1569768 (Python Code)

Max Activating Token Index: 130

Text #3

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.1874. Min Act: -0.1700

Data Index: 1585031 (Python Code)

Max Activating Token Index: 28

Text #4

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.1402. Min Act: -0.1700

Data Index: 1648777 (Python Code)

Max Activating Token Index: 38

Text #5

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.1244. Min Act: -0.1700

Data Index: 1653068 (Python Code)

Max Activating Token Index: 574

Text #6

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.1087. Min Act: -0.1700

Data Index: 1512916 (Python Code)

Max Activating Token Index: 121

Text #7

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.0929. Min Act: -0.1700

Data Index: 1558944 (Python Code)

Max Activating Token Index: 20

Text #8

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.0771. Min Act: -0.1700

Data Index: 1488110 (Python Code)

Max Activating Token Index: 46

Text #9

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.1087. Min Act: -0.1700

Data Index: 1534426 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.0929. Min Act: -0.1700

Data Index: 1295951 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.0771. Min Act: -0.1700

Data Index: 1363489 (Python Code)

Max Activating Token Index: 468

Text #12

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.0771. Min Act: -0.1700

Data Index: 1365780 (Python Code)

Max Activating Token Index: 30

Text #13

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.0613. Min Act: -0.1700

Data Index: 490266 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.0613. Min Act: -0.1700

Data Index: 1427191 (Python Code)

Max Activating Token Index: 756

Text #15

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.0455. Min Act: -0.1700

Data Index: 1386245 (Python Code)

Max Activating Token Index: 373

Text #16

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.0455. Min Act: -0.1700

Data Index: 1456992 (Python Code)

Max Activating Token Index: 814

Text #17

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.0455. Min Act: -0.1700

Data Index: 1598211 (Python Code)

Max Activating Token Index: 472

Text #18

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.0455. Min Act: -0.1700

Data Index: 1360228 (Python Code)

Max Activating Token Index: 923

Text #19

Max Range: 3.2346. Min Range: -3.2346

Max Act: 3.0455. Min Act: -0.1700

Data Index: 1586095 (Python Code)

Max Activating Token Index: 574