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

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

Neuron 896 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: 3.2589. Min Range: -3.2589

Max Act: 3.2589. Min Act: -0.1700

Data Index: 535067 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 3.2589. Min Range: -3.2589

Max Act: 3.1960. Min Act: -0.1700

Data Index: 1223735 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 3.2589. Min Range: -3.2589

Max Act: 3.2117. Min Act: -0.1699

Data Index: 923555 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 3.2589. Min Range: -3.2589

Max Act: 3.1645. Min Act: -0.1700

Data Index: 118181 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 3.2589. Min Range: -3.2589

Max Act: 3.1803. Min Act: -0.1700

Data Index: 961259 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 3.2589. Min Range: -3.2589

Max Act: 3.1488. Min Act: -0.1700

Data Index: 1118055 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 3.2589. Min Range: -3.2589

Max Act: 3.1173. Min Act: -0.1700

Data Index: 1220754 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 3.2589. Min Range: -3.2589

Max Act: 3.1015. Min Act: -0.1700

Data Index: 876116 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 3.2589. Min Range: -3.2589

Max Act: 3.1015. Min Act: -0.1700

Data Index: 984066 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 3.2589. Min Range: -3.2589

Max Act: 3.1173. Min Act: -0.1700

Data Index: 1343929 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 3.2589. Min Range: -3.2589

Max Act: 3.1015. Min Act: -0.1700

Data Index: 1151028 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 3.2589. Min Range: -3.2589

Max Act: 3.1015. Min Act: -0.1700

Data Index: 669499 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 3.2589. Min Range: -3.2589

Max Act: 3.0857. Min Act: -0.1700

Data Index: 242645 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 3.2589. Min Range: -3.2589

Max Act: 3.1015. Min Act: -0.1700

Data Index: 348228 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 3.2589. Min Range: -3.2589

Max Act: 3.0857. Min Act: -0.1700

Data Index: 1338893 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 3.2589. Min Range: -3.2589

Max Act: 3.0857. Min Act: -0.1700

Data Index: 1048948 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 3.2589. Min Range: -3.2589

Max Act: 3.0857. Min Act: -0.1700

Data Index: 126658 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 3.2589. Min Range: -3.2589

Max Act: 3.0857. Min Act: -0.1700

Data Index: 546638 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 3.2589. Min Range: -3.2589

Max Act: 3.0857. Min Act: -0.1700

Data Index: 1084482 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 3.2589. Min Range: -3.2589

Max Act: 3.0542. Min Act: -0.1700

Data Index: 120645 (C4 (Web Text))

Max Activating Token Index: 1019