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

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

Neuron 1485 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.8655. Min Act: -0.1700

Data Index: 1133677 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.8343. Min Act: -0.1700

Data Index: 69804 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.8343. Min Act: -0.1700

Data Index: 315065 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.8030. Min Act: -0.1700

Data Index: 895980 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.8030. Min Act: -0.1700

Data Index: 12250 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.7560. Min Act: -0.1700

Data Index: 582713 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.7091. Min Act: -0.1700

Data Index: 959160 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.7248. Min Act: -0.1700

Data Index: 1354881 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6622. Min Act: -0.1700

Data Index: 160257 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.7091. Min Act: -0.1700

Data Index: 842152 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6778. Min Act: -0.1700

Data Index: 670704 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6309. Min Act: -0.1700

Data Index: 1021183 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6935. Min Act: -0.1700

Data Index: 530090 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6778. Min Act: -0.1700

Data Index: 149851 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6778. Min Act: -0.1700

Data Index: 896084 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6465. Min Act: -0.1700

Data Index: 853285 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.7091. Min Act: -0.1700

Data Index: 434677 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6309. Min Act: -0.1700

Data Index: 1336984 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6309. Min Act: -0.1700

Data Index: 709743 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 3.8655. Min Range: -3.8655

Max Act: 3.6309. Min Act: -0.1700

Data Index: 861582 (C4 (Web Text))

Max Activating Token Index: 511