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

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

Neuron 36 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: 3.2784. Min Range: -3.2784

Max Act: 3.2784. Min Act: -0.1700

Data Index: 908888 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1998. Min Act: -0.1700

Data Index: 1018890 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1998. Min Act: -0.1700

Data Index: 363977 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1368. Min Act: -0.1700

Data Index: 482832 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1368. Min Act: -0.1700

Data Index: 1340758 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1683. Min Act: -0.1700

Data Index: 797759 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1683. Min Act: -0.1700

Data Index: 468718 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1683. Min Act: -0.1700

Data Index: 1212433 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1840. Min Act: -0.1700

Data Index: 1324724 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1683. Min Act: -0.1700

Data Index: 315215 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1526. Min Act: -0.1700

Data Index: 225427 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1526. Min Act: -0.1700

Data Index: 811119 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1210. Min Act: -0.1700

Data Index: 247146 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1053. Min Act: -0.1700

Data Index: 431724 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1210. Min Act: -0.1700

Data Index: 1050163 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.0580. Min Act: -0.1700

Data Index: 968464 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1053. Min Act: -0.1700

Data Index: 178249 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1053. Min Act: -0.1700

Data Index: 1069413 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.0895. Min Act: -0.1700

Data Index: 778905 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.0422. Min Act: -0.1700

Data Index: 795591 (C4 (Web Text))

Max Activating Token Index: 609