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

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

Neuron 1486 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: 3.3453. Min Range: -3.3453

Max Act: 3.3453. Min Act: -0.1700

Data Index: 1027778 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 3.3453. Min Range: -3.3453

Max Act: 3.2982. Min Act: -0.1700

Data Index: 839382 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 3.3453. Min Range: -3.3453

Max Act: 3.2824. Min Act: -0.1700

Data Index: 997286 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 3.3453. Min Range: -3.3453

Max Act: 3.2824. Min Act: -0.1700

Data Index: 163388 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 3.3453. Min Range: -3.3453

Max Act: 3.2667. Min Act: -0.1700

Data Index: 110142 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 3.3453. Min Range: -3.3453

Max Act: 3.2353. Min Act: -0.1700

Data Index: 500182 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 3.3453. Min Range: -3.3453

Max Act: 3.2353. Min Act: -0.1700

Data Index: 442785 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 3.3453. Min Range: -3.3453

Max Act: 3.1881. Min Act: -0.1700

Data Index: 185071 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 3.3453. Min Range: -3.3453

Max Act: 3.2038. Min Act: -0.1700

Data Index: 1221828 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 3.3453. Min Range: -3.3453

Max Act: 3.2038. Min Act: -0.1700

Data Index: 1023570 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 3.3453. Min Range: -3.3453

Max Act: 3.2038. Min Act: -0.1700

Data Index: 409541 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 3.3453. Min Range: -3.3453

Max Act: 3.1724. Min Act: -0.1700

Data Index: 405626 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 3.3453. Min Range: -3.3453

Max Act: 3.1881. Min Act: -0.1700

Data Index: 642539 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 3.3453. Min Range: -3.3453

Max Act: 3.1724. Min Act: -0.1700

Data Index: 140935 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 3.3453. Min Range: -3.3453

Max Act: 3.1881. Min Act: -0.1700

Data Index: 58326 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 3.3453. Min Range: -3.3453

Max Act: 3.1409. Min Act: -0.1700

Data Index: 1012199 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 3.3453. Min Range: -3.3453

Max Act: 3.1566. Min Act: -0.1700

Data Index: 1308507 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 3.3453. Min Range: -3.3453

Max Act: 3.1409. Min Act: -0.1700

Data Index: 874658 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 3.3453. Min Range: -3.3453

Max Act: 3.1094. Min Act: -0.1700

Data Index: 1272896 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 3.3453. Min Range: -3.3453

Max Act: 3.1409. Min Act: -0.1700

Data Index: 1236814 (C4 (Web Text))

Max Activating Token Index: 852