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

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

Neuron 1560 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: 3.7407. Min Range: -3.7407

Max Act: 3.7407. Min Act: -0.1700

Data Index: 689413 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 3.7407. Min Range: -3.7407

Max Act: 3.6155. Min Act: -0.1700

Data Index: 1307021 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 3.7407. Min Range: -3.7407

Max Act: 3.7094. Min Act: -0.1700

Data Index: 718523 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 3.7407. Min Range: -3.7407

Max Act: 3.5842. Min Act: -0.1700

Data Index: 1080889 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 3.7407. Min Range: -3.7407

Max Act: 3.6468. Min Act: -0.1700

Data Index: 435980 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 3.7407. Min Range: -3.7407

Max Act: 3.5842. Min Act: -0.1700

Data Index: 857290 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 3.7407. Min Range: -3.7407

Max Act: 3.5842. Min Act: -0.1700

Data Index: 131847 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 3.7407. Min Range: -3.7407

Max Act: 3.5215. Min Act: -0.1700

Data Index: 1396988 (Python Code)

Max Activating Token Index: 488

Text #8

Max Range: 3.7407. Min Range: -3.7407

Max Act: 3.5529. Min Act: -0.1700

Data Index: 769435 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 3.7407. Min Range: -3.7407

Max Act: 3.4902. Min Act: -0.1700

Data Index: 135516 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 3.7407. Min Range: -3.7407

Max Act: 3.5215. Min Act: -0.1700

Data Index: 1643959 (Python Code)

Max Activating Token Index: 156

Text #11

Max Range: 3.7407. Min Range: -3.7407

Max Act: 3.5215. Min Act: -0.1700

Data Index: 1566316 (Python Code)

Max Activating Token Index: 775

Text #12

Max Range: 3.7407. Min Range: -3.7407

Max Act: 3.4902. Min Act: -0.1700

Data Index: 881630 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 3.7407. Min Range: -3.7407

Max Act: 3.4902. Min Act: -0.1700

Data Index: 1362770 (Python Code)

Max Activating Token Index: 436

Text #14

Max Range: 3.7407. Min Range: -3.7407

Max Act: 3.4432. Min Act: -0.1700

Data Index: 1523685 (Python Code)

Max Activating Token Index: 1022

Text #15

Max Range: 3.7407. Min Range: -3.7407

Max Act: 3.4902. Min Act: -0.1700

Data Index: 129838 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 3.7407. Min Range: -3.7407

Max Act: 3.4588. Min Act: -0.1700

Data Index: 1407739 (Python Code)

Max Activating Token Index: 649

Text #17

Max Range: 3.7407. Min Range: -3.7407

Max Act: 3.5215. Min Act: -0.1700

Data Index: 1395133 (Python Code)

Max Activating Token Index: 802

Text #18

Max Range: 3.7407. Min Range: -3.7407

Max Act: 3.4588. Min Act: -0.1700

Data Index: 945079 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 3.7407. Min Range: -3.7407

Max Act: 3.4588. Min Act: -0.1700

Data Index: 83053 (C4 (Web Text))

Max Activating Token Index: 531