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

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

Neuron 965 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: 5.1699. Min Range: -5.1699

Max Act: 5.1699. Min Act: -0.1679

Data Index: 1422728 (Python Code)

Max Activating Token Index: 664

Text #1

Max Range: 5.1699. Min Range: -5.1699

Max Act: 4.8574. Min Act: -0.1700

Data Index: 511671 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 5.1699. Min Range: -5.1699

Max Act: 4.9199. Min Act: -0.1700

Data Index: 1484941 (Python Code)

Max Activating Token Index: 933

Text #3

Max Range: 5.1699. Min Range: -5.1699

Max Act: 4.7324. Min Act: -0.1699

Data Index: 1580789 (Python Code)

Max Activating Token Index: 167

Text #4

Max Range: 5.1699. Min Range: -5.1699

Max Act: 4.7637. Min Act: -0.1423

Data Index: 1569184 (Python Code)

Max Activating Token Index: 921

Text #5

Max Range: 5.1699. Min Range: -5.1699

Max Act: 4.7012. Min Act: -0.1630

Data Index: 1465451 (Python Code)

Max Activating Token Index: 734

Text #6

Max Range: 5.1699. Min Range: -5.1699

Max Act: 4.7012. Min Act: -0.1700

Data Index: 1538310 (Python Code)

Max Activating Token Index: 180

Text #7

Max Range: 5.1699. Min Range: -5.1699

Max Act: 4.6074. Min Act: -0.1698

Data Index: 1525655 (Python Code)

Max Activating Token Index: 544

Text #8

Max Range: 5.1699. Min Range: -5.1699

Max Act: 4.6387. Min Act: -0.1680

Data Index: 1460506 (Python Code)

Max Activating Token Index: 539

Text #9

Max Range: 5.1699. Min Range: -5.1699

Max Act: 4.5762. Min Act: -0.1700

Data Index: 296511 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 5.1699. Min Range: -5.1699

Max Act: 4.6074. Min Act: -0.1700

Data Index: 1544718 (Python Code)

Max Activating Token Index: 173

Text #11

Max Range: 5.1699. Min Range: -5.1699

Max Act: 4.5449. Min Act: -0.1700

Data Index: 318489 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 5.1699. Min Range: -5.1699

Max Act: 4.5449. Min Act: -0.1700

Data Index: 505953 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 5.1699. Min Range: -5.1699

Max Act: 4.5762. Min Act: -0.1700

Data Index: 698992 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 5.1699. Min Range: -5.1699

Max Act: 4.5449. Min Act: -0.1700

Data Index: 964890 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 5.1699. Min Range: -5.1699

Max Act: 4.5449. Min Act: -0.1700

Data Index: 80099 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 5.1699. Min Range: -5.1699

Max Act: 4.5762. Min Act: -0.1699

Data Index: 1496142 (Python Code)

Max Activating Token Index: 868

Text #17

Max Range: 5.1699. Min Range: -5.1699

Max Act: 4.4980. Min Act: -0.1700

Data Index: 1083498 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 5.1699. Min Range: -5.1699

Max Act: 4.5449. Min Act: -0.1700

Data Index: 1457524 (Python Code)

Max Activating Token Index: 467

Text #19

Max Range: 5.1699. Min Range: -5.1699

Max Act: 4.4824. Min Act: -0.1700

Data Index: 1553317 (Python Code)

Max Activating Token Index: 226