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

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

Neuron 615 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: 3.2888. Min Range: -3.2888

Max Act: 3.2888. Min Act: -0.1700

Data Index: 1302509 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.2573. Min Act: -0.1700

Data Index: 331189 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1787. Min Act: -0.1700

Data Index: 11168 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1944. Min Act: -0.1700

Data Index: 1337147 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1787. Min Act: -0.1700

Data Index: 1011989 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1787. Min Act: -0.1700

Data Index: 1136651 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1472. Min Act: -0.1700

Data Index: 439752 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1314. Min Act: -0.1700

Data Index: 33512 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1314. Min Act: -0.1700

Data Index: 690346 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1472. Min Act: -0.1700

Data Index: 270950 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1314. Min Act: -0.1700

Data Index: 743141 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1472. Min Act: -0.1700

Data Index: 1311478 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1314. Min Act: -0.1700

Data Index: 86061 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1157. Min Act: -0.1700

Data Index: 124000 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.1157. Min Act: -0.1700

Data Index: 1359770 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.0684. Min Act: -0.1700

Data Index: 1299931 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.0684. Min Act: -0.1700

Data Index: 929809 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.0999. Min Act: -0.1700

Data Index: 242897 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.0999. Min Act: -0.1700

Data Index: 111534 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 3.2888. Min Range: -3.2888

Max Act: 3.0842. Min Act: -0.1700

Data Index: 268503 (C4 (Web Text))

Max Activating Token Index: 482