Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 824 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.3822. Min Act: -0.1700

Data Index: 298334 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.4136. Min Act: -0.1700

Data Index: 106957 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.3822. Min Act: -0.1700

Data Index: 848548 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.3822. Min Act: -0.1700

Data Index: 402131 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.3509. Min Act: -0.1700

Data Index: 857366 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.3195. Min Act: -0.1700

Data Index: 101028 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.3195. Min Act: -0.1700

Data Index: 853010 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.3195. Min Act: -0.1700

Data Index: 1265596 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.3509. Min Act: -0.1700

Data Index: 312422 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.3195. Min Act: -0.1700

Data Index: 496607 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.2881. Min Act: -0.1700

Data Index: 1063963 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.2881. Min Act: -0.1700

Data Index: 106758 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.2566. Min Act: -0.1700

Data Index: 563819 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.2566. Min Act: -0.1700

Data Index: 1054070 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.2566. Min Act: -0.1700

Data Index: 977844 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.2409. Min Act: -0.1700

Data Index: 185623 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.2409. Min Act: -0.1700

Data Index: 793544 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.2566. Min Act: -0.1699

Data Index: 850564 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.2252. Min Act: -0.1700

Data Index: 169784 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.2252. Min Act: -0.1700

Data Index: 347794 (C4 (Web Text))

Max Activating Token Index: 1010