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

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

Neuron 98 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.9288. Min Act: -0.1700

Data Index: 753455 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.6160. Min Act: -0.1700

Data Index: 1049219 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.3652. Min Act: -0.1700

Data Index: 599402 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.3652. Min Act: -0.1700

Data Index: 712686 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.3652. Min Act: -0.1700

Data Index: 1220199 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.3338. Min Act: -0.1700

Data Index: 434905 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.2710. Min Act: -0.1700

Data Index: 208281 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.2710. Min Act: -0.1700

Data Index: 740389 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.3024. Min Act: -0.1700

Data Index: 600346 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.3024. Min Act: -0.1700

Data Index: 997204 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.2710. Min Act: -0.1700

Data Index: 646639 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.3024. Min Act: -0.1700

Data Index: 374787 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.2710. Min Act: -0.1700

Data Index: 62779 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.3024. Min Act: -0.1700

Data Index: 767486 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.2710. Min Act: -0.1700

Data Index: 29609 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.2396. Min Act: -0.1700

Data Index: 547849 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.3024. Min Act: -0.1700

Data Index: 721617 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.2396. Min Act: -0.1700

Data Index: 74339 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.3024. Min Act: -0.1700

Data Index: 542340 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 3.9288. Min Range: -3.9288

Max Act: 3.2710. Min Act: -0.1700

Data Index: 696300 (C4 (Web Text))

Max Activating Token Index: 91