Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 220 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.5660. Min Act: -0.1700

Data Index: 78708 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.5347. Min Act: -0.1700

Data Index: 327498 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.5033. Min Act: -0.1700

Data Index: 1312288 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.4720. Min Act: -0.1700

Data Index: 363925 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.4720. Min Act: -0.1700

Data Index: 1333430 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.4406. Min Act: -0.1700

Data Index: 381071 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.3622. Min Act: -0.1700

Data Index: 950071 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.3465. Min Act: -0.1700

Data Index: 133170 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.3308. Min Act: -0.1700

Data Index: 105370 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.2994. Min Act: -0.1700

Data Index: 292248 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.2994. Min Act: -0.1700

Data Index: 340717 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.2837. Min Act: -0.1700

Data Index: 1211952 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.2680. Min Act: -0.1700

Data Index: 799291 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.2523. Min Act: -0.1700

Data Index: 78509 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.2523. Min Act: -0.1700

Data Index: 33400 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.2366. Min Act: -0.1700

Data Index: 1346983 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.2523. Min Act: -0.1700

Data Index: 1100980 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.2523. Min Act: -0.1700

Data Index: 118465 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.2208. Min Act: -0.1700

Data Index: 1210365 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 3.5660. Min Range: -3.5660

Max Act: 3.2208. Min Act: -0.1700

Data Index: 839721 (C4 (Web Text))

Max Activating Token Index: 133