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

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

Neuron 622 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: 5.6382. Min Range: -5.6382

Max Act: 5.6070. Min Act: -0.1700

Data Index: 1613332 (Python Code)

Max Activating Token Index: 521

Text #1

Max Range: 5.6382. Min Range: -5.6382

Max Act: 5.6070. Min Act: -0.1700

Data Index: 1558286 (Python Code)

Max Activating Token Index: 686

Text #2

Max Range: 5.6382. Min Range: -5.6382

Max Act: 5.6382. Min Act: -0.1700

Data Index: 1410153 (Python Code)

Max Activating Token Index: 983

Text #3

Max Range: 5.6382. Min Range: -5.6382

Max Act: 5.5757. Min Act: -0.1700

Data Index: 1383061 (Python Code)

Max Activating Token Index: 29

Text #4

Max Range: 5.6382. Min Range: -5.6382

Max Act: 5.5757. Min Act: -0.1699

Data Index: 1495941 (Python Code)

Max Activating Token Index: 733

Text #5

Max Range: 5.6382. Min Range: -5.6382

Max Act: 5.4820. Min Act: -0.1700

Data Index: 1629737 (Python Code)

Max Activating Token Index: 712

Text #6

Max Range: 5.6382. Min Range: -5.6382

Max Act: 5.5757. Min Act: -0.1700

Data Index: 1492647 (Python Code)

Max Activating Token Index: 473

Text #7

Max Range: 5.6382. Min Range: -5.6382

Max Act: 5.5445. Min Act: -0.1700

Data Index: 1648740 (Python Code)

Max Activating Token Index: 540

Text #8

Max Range: 5.6382. Min Range: -5.6382

Max Act: 5.4820. Min Act: -0.1700

Data Index: 1479470 (Python Code)

Max Activating Token Index: 240

Text #9

Max Range: 5.6382. Min Range: -5.6382

Max Act: 5.4820. Min Act: -0.1700

Data Index: 1495694 (Python Code)

Max Activating Token Index: 683

Text #10

Max Range: 5.6382. Min Range: -5.6382

Max Act: 5.4507. Min Act: -0.1700

Data Index: 1482964 (Python Code)

Max Activating Token Index: 718

Text #11

Max Range: 5.6382. Min Range: -5.6382

Max Act: 5.5132. Min Act: -0.1700

Data Index: 1560260 (Python Code)

Max Activating Token Index: 867

Text #12

Max Range: 5.6382. Min Range: -5.6382

Max Act: 5.5132. Min Act: -0.1700

Data Index: 1432502 (Python Code)

Max Activating Token Index: 269

Text #13

Max Range: 5.6382. Min Range: -5.6382

Max Act: 5.5132. Min Act: -0.1700

Data Index: 1429320 (Python Code)

Max Activating Token Index: 926

Text #14

Max Range: 5.6382. Min Range: -5.6382

Max Act: 5.4507. Min Act: -0.1700

Data Index: 1381314 (Python Code)

Max Activating Token Index: 272

Text #15

Max Range: 5.6382. Min Range: -5.6382

Max Act: 5.4507. Min Act: -0.1700

Data Index: 1656943 (Python Code)

Max Activating Token Index: 931

Text #16

Max Range: 5.6382. Min Range: -5.6382

Max Act: 5.4507. Min Act: -0.1700

Data Index: 1517871 (Python Code)

Max Activating Token Index: 772

Text #17

Max Range: 5.6382. Min Range: -5.6382

Max Act: 5.4195. Min Act: -0.1700

Data Index: 1567433 (Python Code)

Max Activating Token Index: 263

Text #18

Max Range: 5.6382. Min Range: -5.6382

Max Act: 5.4195. Min Act: -0.1700

Data Index: 1561898 (Python Code)

Max Activating Token Index: 1017

Text #19

Max Range: 5.6382. Min Range: -5.6382

Max Act: 5.4195. Min Act: -0.1700

Data Index: 1551377 (Python Code)

Max Activating Token Index: 4