Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1386 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.4784. Min Act: -0.1700

Data Index: 1255055 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.3372. Min Act: -0.1700

Data Index: 133266 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2901. Min Act: -0.1700

Data Index: 735069 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2901. Min Act: -0.1700

Data Index: 622239 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2901. Min Act: -0.1700

Data Index: 870024 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2744. Min Act: -0.1700

Data Index: 912255 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2901. Min Act: -0.1700

Data Index: 503698 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2744. Min Act: -0.1700

Data Index: 778840 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2744. Min Act: -0.1700

Data Index: 680625 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2901. Min Act: -0.1700

Data Index: 894443 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2587. Min Act: -0.1700

Data Index: 255083 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2272. Min Act: -0.1700

Data Index: 1112223 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2587. Min Act: -0.1700

Data Index: 795067 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2429. Min Act: -0.1700

Data Index: 614500 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2429. Min Act: -0.1700

Data Index: 14981 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2587. Min Act: -0.1700

Data Index: 546905 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2744. Min Act: -0.1700

Data Index: 606665 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2744. Min Act: -0.1700

Data Index: 13835 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2587. Min Act: -0.1700

Data Index: 417428 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 3.4784. Min Range: -3.4784

Max Act: 3.2115. Min Act: -0.1700

Data Index: 693002 (C4 (Web Text))

Max Activating Token Index: 784