Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 117 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.4824. Min Act: -0.1700

Data Index: 73831 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.4199. Min Act: -0.1700

Data Index: 1218203 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.4512. Min Act: -0.1700

Data Index: 1306185 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.3574. Min Act: -0.1700

Data Index: 283685 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.4199. Min Act: -0.1700

Data Index: 705778 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.4199. Min Act: -0.1700

Data Index: 1096449 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.3262. Min Act: -0.1700

Data Index: 429944 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.2949. Min Act: -0.1700

Data Index: 1007080 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.2949. Min Act: -0.1700

Data Index: 486030 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.2012. Min Act: -0.1700

Data Index: 505736 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.2324. Min Act: -0.1700

Data Index: 213453 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.2637. Min Act: -0.1700

Data Index: 941535 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.0449. Min Act: -0.1700

Data Index: 964917 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.0449. Min Act: -0.1700

Data Index: 372177 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.1699. Min Act: -0.1700

Data Index: 1023622 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.2012. Min Act: -0.1700

Data Index: 135373 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.2324. Min Act: -0.1700

Data Index: 1115550 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.2637. Min Act: -0.1700

Data Index: 511136 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.1074. Min Act: -0.1700

Data Index: 115930 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 5.4824. Min Range: -5.4824

Max Act: 5.2949. Min Act: -0.1700

Data Index: 11174 (C4 (Web Text))

Max Activating Token Index: 364