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

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

Neuron 1398 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: 3.4718. Min Range: -3.4718

Max Act: 3.4718. Min Act: -0.1700

Data Index: 1101108 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 3.4718. Min Range: -3.4718

Max Act: 3.4405. Min Act: -0.1700

Data Index: 456753 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 3.4718. Min Range: -3.4718

Max Act: 3.3778. Min Act: -0.1700

Data Index: 1301653 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 3.4718. Min Range: -3.4718

Max Act: 3.3621. Min Act: -0.1700

Data Index: 858574 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 3.4718. Min Range: -3.4718

Max Act: 3.2836. Min Act: -0.1700

Data Index: 1086088 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 3.4718. Min Range: -3.4718

Max Act: 3.3307. Min Act: -0.1700

Data Index: 93344 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 3.4718. Min Range: -3.4718

Max Act: 3.3307. Min Act: -0.1700

Data Index: 243685 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 3.4718. Min Range: -3.4718

Max Act: 3.3150. Min Act: -0.1700

Data Index: 764107 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 3.4718. Min Range: -3.4718

Max Act: 3.2836. Min Act: -0.1700

Data Index: 316438 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 3.4718. Min Range: -3.4718

Max Act: 3.2521. Min Act: -0.1700

Data Index: 108445 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 3.4718. Min Range: -3.4718

Max Act: 3.2364. Min Act: -0.1700

Data Index: 887358 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 3.4718. Min Range: -3.4718

Max Act: 3.2364. Min Act: -0.1700

Data Index: 621591 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 3.4718. Min Range: -3.4718

Max Act: 3.2364. Min Act: -0.1700

Data Index: 988856 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 3.4718. Min Range: -3.4718

Max Act: 3.2364. Min Act: -0.1700

Data Index: 1035969 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 3.4718. Min Range: -3.4718

Max Act: 3.2521. Min Act: -0.1700

Data Index: 588835 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 3.4718. Min Range: -3.4718

Max Act: 3.2521. Min Act: -0.1700

Data Index: 1225251 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 3.4718. Min Range: -3.4718

Max Act: 3.2364. Min Act: -0.1700

Data Index: 985203 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 3.4718. Min Range: -3.4718

Max Act: 3.2521. Min Act: -0.1700

Data Index: 743021 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 3.4718. Min Range: -3.4718

Max Act: 3.2050. Min Act: -0.1700

Data Index: 430380 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 3.4718. Min Range: -3.4718

Max Act: 3.2207. Min Act: -0.1700

Data Index: 1056421 (C4 (Web Text))

Max Activating Token Index: 667