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

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

Neuron 1340 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: 3.5857. Min Range: -3.5857

Max Act: 3.5544. Min Act: -0.1700

Data Index: 580710 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.5857. Min Act: -0.1700

Data Index: 547511 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.5387. Min Act: -0.1700

Data Index: 405425 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.5230. Min Act: -0.1700

Data Index: 572810 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.4917. Min Act: -0.1700

Data Index: 1277764 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.4760. Min Act: -0.1700

Data Index: 140508 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.4290. Min Act: -0.1700

Data Index: 574160 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.4447. Min Act: -0.1700

Data Index: 195733 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.4133. Min Act: -0.1700

Data Index: 66368 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.4604. Min Act: -0.1700

Data Index: 592510 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.3819. Min Act: -0.1700

Data Index: 506958 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.4133. Min Act: -0.1700

Data Index: 363678 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.4290. Min Act: -0.1700

Data Index: 498854 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.3506. Min Act: -0.1700

Data Index: 813467 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.3506. Min Act: -0.1700

Data Index: 977455 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.3663. Min Act: -0.1700

Data Index: 995644 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.3819. Min Act: -0.1700

Data Index: 416640 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.3663. Min Act: -0.1700

Data Index: 1139020 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.3819. Min Act: -0.1700

Data Index: 729955 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 3.5857. Min Range: -3.5857

Max Act: 3.3819. Min Act: -0.1700

Data Index: 297276 (C4 (Web Text))

Max Activating Token Index: 398